Reinforcement Learning Libraries - Page 2

PGPortfolio: Policy Gradient Portfolio, the source code of "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem"(https://arxiv.org/pdf/1706.10059.pdf).

Python 1588Updated: 1 y ago License: Strong Copyleft (GPL-3.0)

Solutions of Reinforcement Learning, An Introduction

Jupyter Notebook 1585Updated: 11 mo ago License: Permissive (MIT)

Minimalistic gridworld package for OpenAI Gym

Python 1563Updated: 2 y ago License: Permissive (Apache-2.0)

Collection of reinforcement learning algorithms

Python 1560Updated: 3 y ago License: Permissive (MIT)

Code for the paper "Evolution Strategies as a Scalable Alternative to Reinforcement Learning"

Python 1505Updated: 10 mo ago License: Permissive (MIT)

Artificial intelligence for the Snake game.

Python 1495Updated: 10 mo ago License: Permissive (Apache-2.0)

Python Multi-Agent Reinforcement Learning framework

Python 1471Updated: 10 mo ago License: Permissive (Apache-2.0)

Code for the paper "Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents"

Python 1458Updated: 11 mo ago License: Permissive (MIT)

Environment generation code for the paper "Emergent Tool Use From Multi-Agent Autocurricula"

Python 1454Updated: 11 mo ago License: Permissive (MIT)

Rainbow: Combining Improvements in Deep Reinforcement Learning

Python 1409Updated: 1 y ago License: Permissive (MIT)

Deal or No Deal? End-to-End Learning for Negotiation Dialogues

Python 1364Updated: 1 y ago License: Proprietary (Proprietary)

Author's PyTorch implementation of TD3 for OpenAI gym tasks

Python 1355Updated: 11 mo ago License: Permissive (MIT)

[ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning

Python 1354Updated: 11 mo ago License: Proprietary (Proprietary)

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

Python 1326Updated: 10 mo ago License: Permissive (MIT)

李宏毅《深度强化学习》笔记，在线阅读地址：https://datawhalechina.github.io/leedeeprl-notes/

Python 1323Updated: 3 y ago License: Proprietary (Proprietary)

Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

Python 1275Updated: 10 mo ago License: Permissive (MIT)

For deep RL and the future of AI.

HTML 1272Updated: 11 mo ago License: Permissive (MIT)

Reinforcement Learning Agents in Javascript (Dynamic Programming, Temporal Difference, Deep Q-Learning, Stochastic/Deterministic Policy Gradients)

HTML 1249Updated: 1 y ago License: No License (No License)

Minimalistic gridworld package for OpenAI Gym

Python 1164Updated: 3 y ago License: Permissive (Apache-2.0)

Modular Deep Reinforcement Learning framework in PyTorch. Companion library of the book "Foundations of Deep Reinforcement Learning".

Python 1145Updated: 11 mo ago License: Permissive (MIT)

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

Python 1108Updated: 10 mo ago License: Permissive (MIT)

An LLM-powered autonomous agent platform

TypeScript 1096Updated: 10 mo ago License: Permissive (MIT)

Some basic examples of playing with RL

Python 1086Updated: 12 mo ago License: No License (No License)

A list of StableDiffusion styles and some notes for offline use. Pure HTML, CSS and a bit of JS.

HTML 1085Updated: 10 mo ago License: Permissive (MIT)

PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".

Python 1076Updated: 1 y ago License: Permissive (MIT)

Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch

Python 1067Updated: 10 mo ago License: Permissive (MIT)

A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.

Python 1059Updated: 11 mo ago License: Permissive (MIT)

​TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.

Jupyter Notebook 1044Updated: 11 mo ago License: Proprietary (Proprietary)

PFRL: a PyTorch-based deep reinforcement learning library

Python 1037Updated: 10 mo ago License: Permissive (MIT)

A collection of Reinforcement Learning algorithms from Sutton and Barto's book and other research papers implemented in Python.

Jupyter Notebook 1037Updated: 1 y ago License: No License (No License)

Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation of the Soft Actor-Critic algorithm.

Python 1035Updated: 11 mo ago License: Proprietary (Proprietary)

Python 1025Updated: 11 mo ago License: Permissive (Apache-2.0)

Foundation is a flexible, modular, and composable framework to model socio-economic behaviors and dynamics with both agents and governments. This framework can be used in conjunction with reinforcement learning to learn optimal economic policies, as done by the AI Economist (https://www.einstein.ai/the-ai-economist).

Python 1001Updated: 11 mo ago License: Permissive (BSD-3-Clause)

Contains high quality implementations of Deep Reinforcement Learning algorithms written in PyTorch

Jupyter Notebook 978Updated: 11 mo ago License: No License (No License)

An introductory series to Reinforcement Learning (RL) with comprehensive step-by-step tutorials.

Jupyter Notebook 969Updated: 10 mo ago License: Strong Copyleft (GPL-3.0)

Efficient Batched Reinforcement Learning in TensorFlow

Python 949Updated: 3 y ago License: Permissive (Apache-2.0)

Python driven environment for Live Coding

Python 935Updated: 10 mo ago License: Proprietary (Proprietary)

Isaac Gym Reinforcement Learning Environments

Python 919Updated: 10 mo ago License: Proprietary (Proprietary)

PyTorch implementation of Deep Reinforcement Learning: Policy Gradient methods (TRPO, PPO, A2C) and Generative Adversarial Imitation Learning (GAIL). Fast Fisher vector product TRPO.

Python 911Updated: 11 mo ago License: Permissive (MIT)

Implement AlphaZero/AlphaGo Zero methods on Chinese chess.

Python 909Updated: 10 mo ago License: Strong Copyleft (GPL-3.0)

OpenAI Gym environments for an open-source quadruped robot (SpotMicro)

Python 908Updated: 11 mo ago License: Permissive (Apache-2.0)

Lightweight, efficient and stable implementations of deep reinforcement learning algorithms using PyTorch. 🔥

Python 906Updated: 3 y ago License: Proprietary (Proprietary)

Evolution Strategies Tool

Jupyter Notebook 893Updated: 1 y ago License: Proprietary (Proprietary)

Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments

C++ 890Updated: 11 mo ago License: Permissive (MIT)

Proximal Policy Optimization (PPO) algorithm for Super Mario Bros

Python 889Updated: 11 mo ago License: Permissive (MIT)

Flappy Bird hack using Reinforcement Learning

JavaScript 877Updated: 3 y ago License: No License (No License)

A demo of an GPT-based agent existing in an RPG-like environment

JavaScript 853Updated: 10 mo ago License: No License (No License)

PyGame Learning Environment (PLE) -- Reinforcement Learning Environment in Python.

Python 841Updated: 3 y ago License: Permissive (MIT)

The NetHack Learning Environment

C 839Updated: 1 y ago License: Proprietary (Proprietary)

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

Python 822Updated: 1 y ago License: Permissive (MIT)