Reinforcement Learning Libraries - Page 3

c
chatarenaby chatarena

Python dotstar image 818 dotVersion:Currentdot
License: Permissive (Apache-2.0)

ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.

Support
    Quality
      Security
        License
          Reuse
            m
            metaworldby rlworkgroup

            Python dotstar image 816 dotVersion:Currentdot
            License: Permissive (MIT)

            An open source robotics benchmark for meta- and multi-task reinforcement learning

            Support
              Quality
                Security
                  License
                    Reuse
                      I

                      Python dotstar image 808 dotVersion:Currentdot
                      License: Permissive (MIT)

                      Implementations of selected inverse reinforcement learning algorithms.

                      Support
                        Quality
                          Security
                            License
                              Reuse
                                o
                                on-policyby marlbenchmark

                                Python dotstar image 805 dotVersion:Currentdot
                                License: Permissive (MIT)

                                This is the official implementation of Multi-Agent PPO (MAPPO).

                                Support
                                  Quality
                                    Security
                                      License
                                        Reuse
                                          m
                                          mbrl-libby facebookresearch

                                          Python dotstar image 805 dotVersion:Currentdot
                                          License: Permissive (MIT)

                                          Library for Model Based RL

                                          Support
                                            Quality
                                              Security
                                                License
                                                  Reuse
                                                    S

                                                    Python dotstar image 801 dotVersion:Currentdot
                                                    License: Permissive (MIT)

                                                    Asynchronous Advantage Actor-Critic (A3C) algorithm for Super Mario Bros

                                                    Support
                                                      Quality
                                                        Security
                                                          License
                                                            Reuse
                                                              R
                                                              Reinforceby qqiang00

                                                              Jupyter Notebook dotstar image 796 dotVersion:Currentdot
                                                              no licences License: No License (No License)

                                                              Reinforcement Learning Algorithm Package & PuckWorld, GridWorld Gym environments

                                                              Support
                                                                Quality
                                                                  Security
                                                                    License
                                                                      Reuse
                                                                        i
                                                                        imitationby HumanCompatibleAI

                                                                        Python dotstar image 785 dotVersion:Currentdot
                                                                        License: Permissive (MIT)

                                                                        Clean PyTorch implementations of imitation and reward learning algorithms

                                                                        Support
                                                                          Quality
                                                                            Security
                                                                              License
                                                                                Reuse
                                                                                  p
                                                                                  pytorch-rlby jingweiz

                                                                                  Python dotstar image 784 dotVersion:Currentdot
                                                                                  License: Permissive (MIT)

                                                                                  Deep Reinforcement Learning with pytorch & visdom

                                                                                  Support
                                                                                    Quality
                                                                                      Security
                                                                                        License
                                                                                          Reuse
                                                                                            t
                                                                                            transfuserby autonomousvision

                                                                                            Python dotstar image 784 dotVersion:Currentdot
                                                                                            License: Permissive (MIT)

                                                                                            [PAMI'22] TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving, [CVPR'21] Multi-Modal Fusion Transformer for End-to-End Autonomous Driving

                                                                                            Support
                                                                                              Quality
                                                                                                Security
                                                                                                  License
                                                                                                    Reuse
                                                                                                      o
                                                                                                      osim-rlby stanfordnmbl

                                                                                                      Python dotstar image 778 dotVersion:Currentdot
                                                                                                      License: Permissive (MIT)

                                                                                                      Reinforcement learning environments with musculoskeletal models

                                                                                                      Support
                                                                                                        Quality
                                                                                                          Security
                                                                                                            License
                                                                                                              Reuse
                                                                                                                G
                                                                                                                GibsonEnvby StanfordVL

                                                                                                                C dotstar image 776 dotVersion:Currentdot
                                                                                                                License: Permissive (MIT)

                                                                                                                Gibson Environments: Real-World Perception for Embodied Agents

                                                                                                                Support
                                                                                                                  Quality
                                                                                                                    Security
                                                                                                                      License
                                                                                                                        Reuse
                                                                                                                          s

                                                                                                                          Python dotstar image 775 dotVersion:Currentdot
                                                                                                                          License: Proprietary (Proprietary)

                                                                                                                          Code for "Learning to summarize from human feedback"

                                                                                                                          Support
                                                                                                                            Quality
                                                                                                                              Security
                                                                                                                                License
                                                                                                                                  Reuse
                                                                                                                                    H

                                                                                                                                    Jupyter Notebook dotstar image 767 dotVersion:Currentdot
                                                                                                                                    no licences License: No License (No License)

                                                                                                                                    Master Reinforcement and Deep Reinforcement Learning using OpenAI Gym and TensorFlow

                                                                                                                                    Support
                                                                                                                                      Quality
                                                                                                                                        Security
                                                                                                                                          License
                                                                                                                                            Reuse
                                                                                                                                              R
                                                                                                                                              RLexampleby cuhkrlcourse

                                                                                                                                              Python dotstar image 766 dotVersion:Currentdot
                                                                                                                                              no licences License: No License (No License)

                                                                                                                                              Some basic examples of playing with RL

                                                                                                                                              Support
                                                                                                                                                Quality
                                                                                                                                                  Security
                                                                                                                                                    License
                                                                                                                                                      Reuse
                                                                                                                                                        S
                                                                                                                                                        SMARTSby huawei-noah

                                                                                                                                                        Python dotstar image 759 dotVersion:Currentdot
                                                                                                                                                        License: Permissive (MIT)

                                                                                                                                                        Scalable Multi-Agent RL Training School for Autonomous Driving

                                                                                                                                                        Support
                                                                                                                                                          Quality
                                                                                                                                                            Security
                                                                                                                                                              License
                                                                                                                                                                Reuse
                                                                                                                                                                  P
                                                                                                                                                                  PettingZooby PettingZoo-Team

                                                                                                                                                                  Python dotstar image 757 dotVersion:Currentdot
                                                                                                                                                                  License: Proprietary (Proprietary)

                                                                                                                                                                  Gym for multi-agent reinforcement learning

                                                                                                                                                                  Support
                                                                                                                                                                    Quality
                                                                                                                                                                      Security
                                                                                                                                                                        License
                                                                                                                                                                          Reuse
                                                                                                                                                                            d
                                                                                                                                                                            dreamerv2by danijar

                                                                                                                                                                            Python dotstar image 755 dotVersion:Currentdot
                                                                                                                                                                            License: Permissive (MIT)

                                                                                                                                                                            Mastering Atari with Discrete World Models

                                                                                                                                                                            Support
                                                                                                                                                                              Quality
                                                                                                                                                                                Security
                                                                                                                                                                                  License
                                                                                                                                                                                    Reuse
                                                                                                                                                                                      m

                                                                                                                                                                                      Python dotstar image 746 dotVersion:Currentdot
                                                                                                                                                                                      no licences License: No License (No License)

                                                                                                                                                                                      Code for the paper "Emergent Complexity via Multi-agent Competition"

                                                                                                                                                                                      Support
                                                                                                                                                                                        Quality
                                                                                                                                                                                          Security
                                                                                                                                                                                            License
                                                                                                                                                                                              Reuse
                                                                                                                                                                                                v

                                                                                                                                                                                                Python dotstar image 745 dotVersion:Currentdot
                                                                                                                                                                                                License: Permissive (BSD-2-Clause)

                                                                                                                                                                                                Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.

                                                                                                                                                                                                Support
                                                                                                                                                                                                  Quality
                                                                                                                                                                                                    Security
                                                                                                                                                                                                      License
                                                                                                                                                                                                        Reuse
                                                                                                                                                                                                          R
                                                                                                                                                                                                          RLSeq2Seqby yaserkl

                                                                                                                                                                                                          Python dotstar image 745 dotVersion:Currentdot
                                                                                                                                                                                                          License: Permissive (MIT)

                                                                                                                                                                                                          Deep Reinforcement Learning For Sequence to Sequence Models

                                                                                                                                                                                                          Support
                                                                                                                                                                                                            Quality
                                                                                                                                                                                                              Security
                                                                                                                                                                                                                License
                                                                                                                                                                                                                  Reuse
                                                                                                                                                                                                                    m

                                                                                                                                                                                                                    Jupyter Notebook dotstar image 745 dotVersion:Currentdot
                                                                                                                                                                                                                    License: Permissive (MIT)

                                                                                                                                                                                                                    A multi-task learning example for the paper https://arxiv.org/abs/1705.07115

                                                                                                                                                                                                                    Support
                                                                                                                                                                                                                      Quality
                                                                                                                                                                                                                        Security
                                                                                                                                                                                                                          License
                                                                                                                                                                                                                            Reuse
                                                                                                                                                                                                                              P
                                                                                                                                                                                                                              Popular-RL-Algorithmsby quantumiracle

                                                                                                                                                                                                                              Jupyter Notebook dotstar image 744 dotVersion:Currentdot
                                                                                                                                                                                                                              License: Permissive (Apache-2.0)

                                                                                                                                                                                                                              PyTorch implementation of Soft Actor-Critic (SAC), Twin Delayed DDPG (TD3), Actor-Critic (AC/A2C), Proximal Policy Optimization (PPO), QT-Opt, PointNet..

                                                                                                                                                                                                                              Support
                                                                                                                                                                                                                                Quality
                                                                                                                                                                                                                                  Security
                                                                                                                                                                                                                                    License
                                                                                                                                                                                                                                      Reuse
                                                                                                                                                                                                                                        p
                                                                                                                                                                                                                                        pytorch-maml-rlby tristandeleu

                                                                                                                                                                                                                                        Python dotstar image 722 dotVersion:Currentdot
                                                                                                                                                                                                                                        License: Permissive (MIT)

                                                                                                                                                                                                                                        Reinforcement Learning with Model-Agnostic Meta-Learning in Pytorch

                                                                                                                                                                                                                                        Support
                                                                                                                                                                                                                                          Quality
                                                                                                                                                                                                                                            Security
                                                                                                                                                                                                                                              License
                                                                                                                                                                                                                                                Reuse
                                                                                                                                                                                                                                                  p
                                                                                                                                                                                                                                                  playgroundby MultiAgentLearning

                                                                                                                                                                                                                                                  Python dotstar image 722 dotVersion:Currentdot
                                                                                                                                                                                                                                                  License: Permissive (Apache-2.0)

                                                                                                                                                                                                                                                  PlayGround: AI Research into Multi-Agent Learning.

                                                                                                                                                                                                                                                  Support
                                                                                                                                                                                                                                                    Quality
                                                                                                                                                                                                                                                      Security
                                                                                                                                                                                                                                                        License
                                                                                                                                                                                                                                                          Reuse
                                                                                                                                                                                                                                                            m
                                                                                                                                                                                                                                                            maroby microsoft

                                                                                                                                                                                                                                                            Python dotstar image 716 dotVersion:Currentdot
                                                                                                                                                                                                                                                            License: Permissive (MIT)

                                                                                                                                                                                                                                                            Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.

                                                                                                                                                                                                                                                            Support
                                                                                                                                                                                                                                                              Quality
                                                                                                                                                                                                                                                                Security
                                                                                                                                                                                                                                                                  License
                                                                                                                                                                                                                                                                    Reuse
                                                                                                                                                                                                                                                                      t
                                                                                                                                                                                                                                                                      torchbeastby facebookresearch

                                                                                                                                                                                                                                                                      Python dotstar image 714 dotVersion:Currentdot
                                                                                                                                                                                                                                                                      License: Permissive (Apache-2.0)

                                                                                                                                                                                                                                                                      A PyTorch Platform for Distributed RL

                                                                                                                                                                                                                                                                      Support
                                                                                                                                                                                                                                                                        Quality
                                                                                                                                                                                                                                                                          Security
                                                                                                                                                                                                                                                                            License
                                                                                                                                                                                                                                                                              Reuse
                                                                                                                                                                                                                                                                                l

                                                                                                                                                                                                                                                                                Python dotstar image 712 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                no licences License: No License (No License)

                                                                                                                                                                                                                                                                                Code for the paper "Large-Scale Study of Curiosity-Driven Learning"

                                                                                                                                                                                                                                                                                Support
                                                                                                                                                                                                                                                                                  Quality
                                                                                                                                                                                                                                                                                    Security
                                                                                                                                                                                                                                                                                      License
                                                                                                                                                                                                                                                                                        Reuse
                                                                                                                                                                                                                                                                                          D

                                                                                                                                                                                                                                                                                          Jupyter Notebook dotstar image 710 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                          License: Permissive (MIT)

                                                                                                                                                                                                                                                                                          Notes for the Reinforcement Learning course by David Silver along with implementation of various algorithms.

                                                                                                                                                                                                                                                                                          Support
                                                                                                                                                                                                                                                                                            Quality
                                                                                                                                                                                                                                                                                              Security
                                                                                                                                                                                                                                                                                                License
                                                                                                                                                                                                                                                                                                  Reuse
                                                                                                                                                                                                                                                                                                    m
                                                                                                                                                                                                                                                                                                    mpc.pytorchby locuslab

                                                                                                                                                                                                                                                                                                    Python dotstar image 693 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                    License: Permissive (MIT)

                                                                                                                                                                                                                                                                                                    A fast and differentiable model predictive control (MPC) solver for PyTorch.

                                                                                                                                                                                                                                                                                                    Support
                                                                                                                                                                                                                                                                                                      Quality
                                                                                                                                                                                                                                                                                                        Security
                                                                                                                                                                                                                                                                                                          License
                                                                                                                                                                                                                                                                                                            Reuse
                                                                                                                                                                                                                                                                                                              m
                                                                                                                                                                                                                                                                                                              mushroom-rlby MushroomRL

                                                                                                                                                                                                                                                                                                              Python dotstar image 685 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                              License: Permissive (MIT)

                                                                                                                                                                                                                                                                                                              Python library for Reinforcement Learning.

                                                                                                                                                                                                                                                                                                              Support
                                                                                                                                                                                                                                                                                                                Quality
                                                                                                                                                                                                                                                                                                                  Security
                                                                                                                                                                                                                                                                                                                    License
                                                                                                                                                                                                                                                                                                                      Reuse
                                                                                                                                                                                                                                                                                                                        l
                                                                                                                                                                                                                                                                                                                        llm_agentsby mpaepper

                                                                                                                                                                                                                                                                                                                        Python dotstar image 680 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                                        License: Permissive (MIT)

                                                                                                                                                                                                                                                                                                                        Build agents which are controlled by LLMs

                                                                                                                                                                                                                                                                                                                        Support
                                                                                                                                                                                                                                                                                                                          Quality
                                                                                                                                                                                                                                                                                                                            Security
                                                                                                                                                                                                                                                                                                                              License
                                                                                                                                                                                                                                                                                                                                Reuse
                                                                                                                                                                                                                                                                                                                                  H

                                                                                                                                                                                                                                                                                                                                  Jupyter Notebook dotstar image 674 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                                                  License: Permissive (MIT)

                                                                                                                                                                                                                                                                                                                                  Hands-On Reinforcement Learning with Python, published by Packt

                                                                                                                                                                                                                                                                                                                                  Support
                                                                                                                                                                                                                                                                                                                                    Quality
                                                                                                                                                                                                                                                                                                                                      Security
                                                                                                                                                                                                                                                                                                                                        License
                                                                                                                                                                                                                                                                                                                                          Reuse
                                                                                                                                                                                                                                                                                                                                            g
                                                                                                                                                                                                                                                                                                                                            gym-tradingby hackthemarket

                                                                                                                                                                                                                                                                                                                                            Jupyter Notebook dotstar image 662 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                                                            License: Permissive (MIT)

                                                                                                                                                                                                                                                                                                                                            Environment for reinforcement-learning algorithmic trading models

                                                                                                                                                                                                                                                                                                                                            Support
                                                                                                                                                                                                                                                                                                                                              Quality
                                                                                                                                                                                                                                                                                                                                                Security
                                                                                                                                                                                                                                                                                                                                                  License
                                                                                                                                                                                                                                                                                                                                                    Reuse
                                                                                                                                                                                                                                                                                                                                                      P

                                                                                                                                                                                                                                                                                                                                                      Python dotstar image 656 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                                                                      no licences License: No License (No License)

                                                                                                                                                                                                                                                                                                                                                      PythonLinearNonLinearControl is a library implementing the linear and nonlinear control theories in python.

                                                                                                                                                                                                                                                                                                                                                      Support
                                                                                                                                                                                                                                                                                                                                                        Quality
                                                                                                                                                                                                                                                                                                                                                          Security
                                                                                                                                                                                                                                                                                                                                                            License
                                                                                                                                                                                                                                                                                                                                                              Reuse
                                                                                                                                                                                                                                                                                                                                                                R
                                                                                                                                                                                                                                                                                                                                                                Replicating-DeepMindby kristjankorjus

                                                                                                                                                                                                                                                                                                                                                                C++ dotstar image 653 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                                                                                License: Strong Copyleft (GPL-3.0)

                                                                                                                                                                                                                                                                                                                                                                Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind

                                                                                                                                                                                                                                                                                                                                                                Support
                                                                                                                                                                                                                                                                                                                                                                  Quality
                                                                                                                                                                                                                                                                                                                                                                    Security
                                                                                                                                                                                                                                                                                                                                                                      License
                                                                                                                                                                                                                                                                                                                                                                        Reuse
                                                                                                                                                                                                                                                                                                                                                                          b
                                                                                                                                                                                                                                                                                                                                                                          babyagi-asiby oliveirabruno01

                                                                                                                                                                                                                                                                                                                                                                          Python dotstar image 650 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                                                                                          License: Permissive (MIT)

                                                                                                                                                                                                                                                                                                                                                                          BabyAGI: an Autonomous and Self-Improving agent, or BASI

                                                                                                                                                                                                                                                                                                                                                                          Support
                                                                                                                                                                                                                                                                                                                                                                            Quality
                                                                                                                                                                                                                                                                                                                                                                              Security
                                                                                                                                                                                                                                                                                                                                                                                License
                                                                                                                                                                                                                                                                                                                                                                                  Reuse
                                                                                                                                                                                                                                                                                                                                                                                    C
                                                                                                                                                                                                                                                                                                                                                                                    CityFlowby cityflow-project

                                                                                                                                                                                                                                                                                                                                                                                    C++ dotstar image 646 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                                                                                                    License: Permissive (Apache-2.0)

                                                                                                                                                                                                                                                                                                                                                                                    A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario

                                                                                                                                                                                                                                                                                                                                                                                    Support
                                                                                                                                                                                                                                                                                                                                                                                      Quality
                                                                                                                                                                                                                                                                                                                                                                                        Security
                                                                                                                                                                                                                                                                                                                                                                                          License
                                                                                                                                                                                                                                                                                                                                                                                            Reuse
                                                                                                                                                                                                                                                                                                                                                                                              c
                                                                                                                                                                                                                                                                                                                                                                                              contextualbanditsby david-cortes

                                                                                                                                                                                                                                                                                                                                                                                              Python dotstar image 636 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                                                                                                              License: Permissive (BSD-2-Clause)

                                                                                                                                                                                                                                                                                                                                                                                              Python implementations of contextual bandits algorithms

                                                                                                                                                                                                                                                                                                                                                                                              Support
                                                                                                                                                                                                                                                                                                                                                                                                Quality
                                                                                                                                                                                                                                                                                                                                                                                                  Security
                                                                                                                                                                                                                                                                                                                                                                                                    License
                                                                                                                                                                                                                                                                                                                                                                                                      Reuse
                                                                                                                                                                                                                                                                                                                                                                                                        N
                                                                                                                                                                                                                                                                                                                                                                                                        Neural-SLAMby devendrachaplot

                                                                                                                                                                                                                                                                                                                                                                                                        Python dotstar image 628 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                                                                                                                        License: Permissive (MIT)

                                                                                                                                                                                                                                                                                                                                                                                                        Pytorch code for ICLR-20 Paper "Learning to Explore using Active Neural SLAM"

                                                                                                                                                                                                                                                                                                                                                                                                        Support
                                                                                                                                                                                                                                                                                                                                                                                                          Quality
                                                                                                                                                                                                                                                                                                                                                                                                            Security
                                                                                                                                                                                                                                                                                                                                                                                                              License
                                                                                                                                                                                                                                                                                                                                                                                                                Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                  D
                                                                                                                                                                                                                                                                                                                                                                                                                  DI-driveby opendilab

                                                                                                                                                                                                                                                                                                                                                                                                                  Python dotstar image 625 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                                                                                                                                  License: Permissive (Apache-2.0)

                                                                                                                                                                                                                                                                                                                                                                                                                  Decision Intelligence Platform for Autonomous Driving simulation.

                                                                                                                                                                                                                                                                                                                                                                                                                  Support
                                                                                                                                                                                                                                                                                                                                                                                                                    Quality
                                                                                                                                                                                                                                                                                                                                                                                                                      Security
                                                                                                                                                                                                                                                                                                                                                                                                                        License
                                                                                                                                                                                                                                                                                                                                                                                                                          Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                            R
                                                                                                                                                                                                                                                                                                                                                                                                                            RosettaStoneby utilForever

                                                                                                                                                                                                                                                                                                                                                                                                                            C++ dotstar image 616 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                                                                                                                                            License: Strong Copyleft (AGPL-3.0)

                                                                                                                                                                                                                                                                                                                                                                                                                            Hearthstone simulator using C++ with some reinforcement learning

                                                                                                                                                                                                                                                                                                                                                                                                                            Support
                                                                                                                                                                                                                                                                                                                                                                                                                              Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                Security
                                                                                                                                                                                                                                                                                                                                                                                                                                  License
                                                                                                                                                                                                                                                                                                                                                                                                                                    Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                      s
                                                                                                                                                                                                                                                                                                                                                                                                                                      slimevolleygymby hardmaru

                                                                                                                                                                                                                                                                                                                                                                                                                                      Python dotstar image 612 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                                                                                                                                                      License: Permissive (Apache-2.0)

                                                                                                                                                                                                                                                                                                                                                                                                                                      A simple OpenAI Gym environment for single and multi-agent reinforcement learning

                                                                                                                                                                                                                                                                                                                                                                                                                                      Support
                                                                                                                                                                                                                                                                                                                                                                                                                                        Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                          Security
                                                                                                                                                                                                                                                                                                                                                                                                                                            License
                                                                                                                                                                                                                                                                                                                                                                                                                                              Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                s
                                                                                                                                                                                                                                                                                                                                                                                                                                                s2protocolby Blizzard

                                                                                                                                                                                                                                                                                                                                                                                                                                                Python dotstar image 600 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                                                                                                                                                                License: Permissive (MIT)

                                                                                                                                                                                                                                                                                                                                                                                                                                                Python library to decode StarCraft II replay protocols

                                                                                                                                                                                                                                                                                                                                                                                                                                                Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                  Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                    Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                      License
                                                                                                                                                                                                                                                                                                                                                                                                                                                        Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                          p
                                                                                                                                                                                                                                                                                                                                                                                                                                                          pybullet-gymby benelot

                                                                                                                                                                                                                                                                                                                                                                                                                                                          Python dotstar image 600 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                                                                                                                                                                          License: Proprietary (Proprietary)

                                                                                                                                                                                                                                                                                                                                                                                                                                                          Open-source implementations of OpenAI Gym MuJoCo environments for use with the OpenAI Gym Reinforcement Learning Research Platform.

                                                                                                                                                                                                                                                                                                                                                                                                                                                          Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                            Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                              Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                    a

                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Python dotstar image 594 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                                                                                                                                                                                    License: Permissive (MIT)

                                                                                                                                                                                                                                                                                                                                                                                                                                                                    A PyTorch library for building deep reinforcement learning agents.

                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                          License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                              p

                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Python dotstar image 586 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                                                                                                                                                                                              License: Permissive (MIT)

                                                                                                                                                                                                                                                                                                                                                                                                                                                                              PyTorch implementation of soft actor critic

                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        r

                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Python dotstar image 580 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        no licences License: No License (No License)

                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        This repository contains most of pytorch implementation based classic deep reinforcement learning algorithms, including - DQN, DDQN, Dueling Network, DDPG, SAC, A2C, PPO, TRPO. (More algorithms are still in progress)

                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  s
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  sample-factoryby alex-petrenko

                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Python dotstar image 574 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  License: Permissive (MIT)

                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  High throughput synchronous and asynchronous reinforcement learning

                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            f
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            fast_abs_rlby ChenRocks

                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Python dotstar image 574 dotVersion:Currentdot
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            License: Permissive (MIT)

                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Code for ACL 2018 paper: "Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting. Chen and Bansal"

                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      c
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      chatarenaby chatarena
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Pythondotstar image 818dotUpdated: 9 mo agodot License: Permissive (Apache-2.0)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                m
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                metaworldby rlworkgroup
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                An open source robotics benchmark for meta- and multi-task reinforcement learning
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Pythondotstar image 816dotUpdated: 1 y agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          I
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Inverse-Reinforcement-Learningby MatthewJA
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Implementations of selected inverse reinforcement learning algorithms.
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Pythondotstar image 808dotUpdated: 10 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    o
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    on-policyby marlbenchmark
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    This is the official implementation of Multi-Agent PPO (MAPPO).
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Pythondotstar image 805dotUpdated: 9 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              m
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              mbrl-libby facebookresearch
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Library for Model Based RL
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Pythondotstar image 805dotUpdated: 9 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        S
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Super-mario-bros-A3C-pytorchby uvipen
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Asynchronous Advantage Actor-Critic (A3C) algorithm for Super Mario Bros
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Pythondotstar image 801dotUpdated: 3 y agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  R
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Reinforceby qqiang00
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Reinforcement Learning Algorithm Package & PuckWorld, GridWorld Gym environments
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Jupyter Notebookdotstar image 796dotUpdated: 9 mo agodotno licences License: No License (No License)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            i
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            imitationby HumanCompatibleAI
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Clean PyTorch implementations of imitation and reward learning algorithms
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Pythondotstar image 785dotUpdated: 10 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      p
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      pytorch-rlby jingweiz
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Deep Reinforcement Learning with pytorch & visdom
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Pythondotstar image 784dotUpdated: 1 y agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                t
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                transfuserby autonomousvision
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                [PAMI'22] TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving, [CVPR'21] Multi-Modal Fusion Transformer for End-to-End Autonomous Driving
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Pythondotstar image 784dotUpdated: 10 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          o
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          osim-rlby stanfordnmbl
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Reinforcement learning environments with musculoskeletal models
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Pythondotstar image 778dotUpdated: 3 y agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    G
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    GibsonEnvby StanfordVL
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Gibson Environments: Real-World Perception for Embodied Agents
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Cdotstar image 776dotUpdated: 9 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              s
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              summarize-from-feedbackby openai
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Code for "Learning to summarize from human feedback"
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Pythondotstar image 775dotUpdated: 9 mo agodot License: Proprietary (Proprietary)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        H
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Hands-On-Reinforcement-Learning-With-Pythonby sudharsan13296
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Master Reinforcement and Deep Reinforcement Learning using OpenAI Gym and TensorFlow
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Jupyter Notebookdotstar image 767dotUpdated: 10 mo agodotno licences License: No License (No License)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  R
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  RLexampleby cuhkrlcourse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Some basic examples of playing with RL
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Pythondotstar image 766dotUpdated: 3 y agodotno licences License: No License (No License)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            S
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            SMARTSby huawei-noah
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Scalable Multi-Agent RL Training School for Autonomous Driving
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Pythondotstar image 759dotUpdated: 9 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      P
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      PettingZooby PettingZoo-Team
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Gym for multi-agent reinforcement learning
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Pythondotstar image 757dotUpdated: 3 y agodot License: Proprietary (Proprietary)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                d
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                dreamerv2by danijar
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Mastering Atari with Discrete World Models
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Pythondotstar image 755dotUpdated: 11 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          m
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          multiagent-competitionby openai
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Code for the paper "Emergent Complexity via Multi-agent Competition"
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Pythondotstar image 746dotUpdated: 1 y agodotno licences License: No License (No License)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    v
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    visual-pushing-graspingby andyzeng
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Pythondotstar image 745dotUpdated: 11 mo agodot License: Permissive (BSD-2-Clause)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              R
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              RLSeq2Seqby yaserkl
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Deep Reinforcement Learning For Sequence to Sequence Models
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Pythondotstar image 745dotUpdated: 10 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        m
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        multi-task-learning-exampleby yaringal
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        A multi-task learning example for the paper https://arxiv.org/abs/1705.07115
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Jupyter Notebookdotstar image 745dotUpdated: 1 y agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  P
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Popular-RL-Algorithmsby quantumiracle
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  PyTorch implementation of Soft Actor-Critic (SAC), Twin Delayed DDPG (TD3), Actor-Critic (AC/A2C), Proximal Policy Optimization (PPO), QT-Opt, PointNet..
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Jupyter Notebookdotstar image 744dotUpdated: 10 mo agodot License: Permissive (Apache-2.0)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            p
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            pytorch-maml-rlby tristandeleu
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Reinforcement Learning with Model-Agnostic Meta-Learning in Pytorch
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Pythondotstar image 722dotUpdated: 11 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      p
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      playgroundby MultiAgentLearning
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      PlayGround: AI Research into Multi-Agent Learning.
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Pythondotstar image 722dotUpdated: 11 mo agodot License: Permissive (Apache-2.0)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                m
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                maroby microsoft
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Pythondotstar image 716dotUpdated: 10 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          t
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          torchbeastby facebookresearch
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          A PyTorch Platform for Distributed RL
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Pythondotstar image 714dotUpdated: 11 mo agodot License: Permissive (Apache-2.0)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    l
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    large-scale-curiosityby openai
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Code for the paper "Large-Scale Study of Curiosity-Driven Learning"
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Pythondotstar image 712dotUpdated: 3 y agodotno licences License: No License (No License)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              D
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              David-Silver-Reinforcement-learningby dalmia
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Notes for the Reinforcement Learning course by David Silver along with implementation of various algorithms.
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Jupyter Notebookdotstar image 710dotUpdated: 1 y agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        m
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        mpc.pytorchby locuslab
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        A fast and differentiable model predictive control (MPC) solver for PyTorch.
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Pythondotstar image 693dotUpdated: 10 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  m
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  mushroom-rlby MushroomRL
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Python library for Reinforcement Learning.
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Pythondotstar image 685dotUpdated: 9 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            l
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            llm_agentsby mpaepper
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Build agents which are controlled by LLMs
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Pythondotstar image 680dotUpdated: 10 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      H
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Hands-On-Reinforcement-Learning-with-Pythonby PacktPublishing
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Hands-On Reinforcement Learning with Python, published by Packt
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Jupyter Notebookdotstar image 674dotUpdated: 1 y agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                g
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                gym-tradingby hackthemarket
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Environment for reinforcement-learning algorithmic trading models
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Jupyter Notebookdotstar image 662dotUpdated: 11 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          P
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          PythonLinearNonlinearControlby Shunichi09
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          PythonLinearNonLinearControl is a library implementing the linear and nonlinear control theories in python.
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Pythondotstar image 656dotUpdated: 9 mo agodotno licences License: No License (No License)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    R
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Replicating-DeepMindby kristjankorjus
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    C++dotstar image 653dotUpdated: 3 y agodot License: Strong Copyleft (GPL-3.0)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              b
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              babyagi-asiby oliveirabruno01
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              BabyAGI: an Autonomous and Self-Improving agent, or BASI
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Pythondotstar image 650dotUpdated: 9 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        C
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        CityFlowby cityflow-project
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        C++dotstar image 646dotUpdated: 10 mo agodot License: Permissive (Apache-2.0)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  c
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  contextualbanditsby david-cortes
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Python implementations of contextual bandits algorithms
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Pythondotstar image 636dotUpdated: 10 mo agodot License: Permissive (BSD-2-Clause)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            N
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Neural-SLAMby devendrachaplot
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Pytorch code for ICLR-20 Paper "Learning to Explore using Active Neural SLAM"
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Pythondotstar image 628dotUpdated: 9 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      D
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      DI-driveby opendilab
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Decision Intelligence Platform for Autonomous Driving simulation.
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Pythondotstar image 625dotUpdated: 9 mo agodot License: Permissive (Apache-2.0)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                R
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                RosettaStoneby utilForever
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Hearthstone simulator using C++ with some reinforcement learning
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                C++dotstar image 616dotUpdated: 1 y agodot License: Strong Copyleft (AGPL-3.0)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          s
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          slimevolleygymby hardmaru
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          A simple OpenAI Gym environment for single and multi-agent reinforcement learning
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Pythondotstar image 612dotUpdated: 1 y agodot License: Permissive (Apache-2.0)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    s
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    s2protocolby Blizzard
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Python library to decode StarCraft II replay protocols
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Pythondotstar image 600dotUpdated: 11 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              p
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              pybullet-gymby benelot
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Open-source implementations of OpenAI Gym MuJoCo environments for use with the OpenAI Gym Reinforcement Learning Research Platform.
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Pythondotstar image 600dotUpdated: 3 y agodot License: Proprietary (Proprietary)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        a
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        autonomous-learning-libraryby cpnota
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        A PyTorch library for building deep reinforcement learning agents.
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Pythondotstar image 594dotUpdated: 10 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  p
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  pytorch-soft-actor-criticby pranz24
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  PyTorch implementation of soft actor critic
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Pythondotstar image 586dotUpdated: 1 y agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            r
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            reinforcement-learning-algorithmsby TianhongDai
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            This repository contains most of pytorch implementation based classic deep reinforcement learning algorithms, including - DQN, DDQN, Dueling Network, DDPG, SAC, A2C, PPO, TRPO. (More algorithms are still in progress)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Pythondotstar image 580dotUpdated: 1 y agodotno licences License: No License (No License)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      s
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      sample-factoryby alex-petrenko
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      High throughput synchronous and asynchronous reinforcement learning
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Pythondotstar image 574dotUpdated: 10 mo agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              Reuse
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                f
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                fast_abs_rlby ChenRocks
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Code for ACL 2018 paper: "Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting. Chen and Bansal"
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Pythondotstar image 574dotUpdated: 3 y agodot License: Permissive (MIT)
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                Support
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  Quality
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    Security
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      License
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        Reuse