TensorSwarm: A framework for reinforcement learning of robot swarms.
Support
Quality
Security
License
Reuse
A study of the overhead incurred by various PHP frameworks.
Support
Quality
Security
License
Reuse
PGE: Parallel Game Engine
Support
Quality
Security
License
Reuse
Adversarial Imitation Via Variational Inverse Reinforcement Learning
Support
Quality
Security
License
Reuse
CLEVR-Robot: a reinforcement learning environment combining vision, language and control.
Support
Quality
Security
License
Reuse
Explore and find reinforcement learning environments in a list of 150+ open source environments.
Support
Quality
Security
License
Reuse
R
Reinforcement-Learning-for-Tradingby nicknochnack
Jupyter Notebook 
87 Version:Current
License: No License (No License)
License: No License (No License)A walkthrough of using the gym-anytrading environment for reinforcement learning applications leveraging custom datasets.
Support
Quality
Security
License
Reuse
AuctionGym is a simulation environment that enables reproducible evaluation of bandit and reinforcement learning methods for online advertising auctions.
Support
Quality
Security
License
Reuse
Autonomous Navigation of UAV using Reinforcement Learning algorithms.
Support
Quality
Security
License
Reuse
Level-based Foraging (LBF): A multi-agent environment for RL
Support
Quality
Security
License
Reuse
SARL*: Deep RL based human-aware navigation for mobile robot in crowded indoor environments implemented in ROS.
Support
Quality
Security
License
Reuse
Benchmarking RL generalization in an interpretable way.
Support
Quality
Security
License
Reuse
Reinforcement Learning Tutorial on Super Mario
Support
Quality
Security
License
Reuse
openai/gym's popular toolkit for developing and comparing reinforcement learning algorithms port to C#.
Support
Quality
Security
License
Reuse
deep reinforcement learning for personal research
Support
Quality
Security
License
Reuse
A large collection of mostly reinforcement learning agents.
Support
Quality
Security
License
Reuse
Augmented environments with RL
Support
Quality
Security
License
Reuse
Support
Quality
Security
License
Reuse
Graph Neural Network architecture to solve the decision variant of the Traveling Salesperson Problem (is there a Hamiltonian tour in G with up to a given cost?)
Support
Quality
Security
License
Reuse
Reason8.ai PyTorch solution for NIPS RL 2017 challenge
Support
Quality
Security
License
Reuse
Support
Quality
Security
License
Reuse
Actor-critic trained w PPO on OpenAI's Procgen Benchmark (PyTorch). Built from scratch.
Support
Quality
Security
License
Reuse
R
Reinforcement_Learningby abhisheksuran
Jupyter Notebook 84 Version:Current License: No License (No License)
License: No License (No License)Deep Reinforcement Learning Algorithms implemented with Tensorflow 2.3
Support
Quality
Security
License
Reuse
g
gym-continuousDoubleAuctionby ChuaCheowHuan
Jupyter Notebook 84 Version:Current License: Permissive (MIT)
A custom MARL (multi-agent reinforcement learning) environment where multiple agents trade against one another (self-play) in a zero-sum continuous double auction. Ray [RLlib] is used for training.
Support
Quality
Security
License
Reuse
A Reinforcement Learning agent that learns how to to solve maze missions in Minecraft.
Support
Quality
Security
License
Reuse
Implementing reinforcement-learning algorithms for pysc2 -environment
Support
Quality
Security
License
Reuse
Implementation of reinforcement learning approach to make a car learn to drive
Support
Quality
Security
License
Reuse
Open source domain randomized door opening training environment
Support
Quality
Security
License
Reuse
Code for "Multi-task Reinforcement Learning with Soft Modularization"
Support
Quality
Security
License
Reuse
Support
Quality
Security
License
Reuse
Reinforcement Learning Assembly
Support
Quality
Security
License
Reuse
An open-source platform for applying Reinforcement Learning for Grid Control (RLGC)
Support
Quality
Security
License
Reuse
B
BinPacking_Neural_Combinatorial_Optimizationby rubensolozabal
Python 82 Version:Current License: Permissive (MIT)
Bin Packing Problem using Neural Combinatorial Optimization.
Support
Quality
Security
License
Reuse
An RL agent for the Google Football environment
Support
Quality
Security
License
Reuse
Reinforcement learning material, code and exercises for Udacity Nanodegree programs.
Support
Quality
Security
License
Reuse
Evaluating long-term memory of reinforcement learning algorithms
Support
Quality
Security
License
Reuse
M
Multi-Agent-Reinforcement-Learningby yangchen1997
Python 82 Version:Current License: Permissive (MIT)
PyTorch implements multi-agent reinforcement learning algorithms, including QMIX, Independent PPO, Centralized PPO, Grid Wise Control, Grid Wise Control+PPO, Grid Wise Control+DDPG.
Support
Quality
Security
License
Reuse
AirSim with openAI gym and keras-rl integration for autonomous copter RL
Support
Quality
Security
License
Reuse
A Trading environment base on Gym
Support
Quality
Security
License
Reuse
Model-Based Generative Adversarial Imitation Learning
Support
Quality
Security
License
Reuse
An OpenAI-gym-like environment for Little Fighter 2
Support
Quality
Security
License
Reuse
Support
Quality
Security
License
Reuse
A
Autonomous-Driftingby kanakkabara
Jupyter Notebook 81 Version:Current License: No License (No License)
License: No License (No License)Autonomous Drifting using Reinforcement Learning
Support
Quality
Security
License
Reuse
Combining deep learning and reinforcement learning.
Support
Quality
Security
License
Reuse
codes for the paper "POMO: Policy Optimization with Multiple Optima for Reinforcement Learning"
Support
Quality
Security
License
Reuse
A
Python 80 Version:Current License: No License (No License)
License: No License (No License)RL library based on algorithms from the book <A-introduction-to-reinforcement-learning>
Support
Quality
Security
License
Reuse
N
Neural-Lyapunov-Controlby YaChienChang
Jupyter Notebook 80 Version:Current License: No License (No License)
License: No License (No License)Learning Lyapunov functions and control policies of nonlinear dynamical systems
Support
Quality
Security
License
Reuse
The Reinforcement Learning environment for the popular Real-time Strategy game simulator μRTS
Support
Quality
Security
License
Reuse
megastep helps you build 1-million FPS reinforcement learning environments on a single GPU
Support
Quality
Security
License
Reuse
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning
Support
Quality
Security
License
Reuse
T
TensorSwarmby TensorSwarm
TensorSwarm: A framework for reinforcement learning of robot swarms.
Python 88Updated: 4 y ago License: Permissive (MIT)
88Updated: 4 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
p
php-framework-benchmarksby pmjones
A study of the overhead incurred by various PHP frameworks.
PHP 88Updated: 5 y ago License: No License (No License)
88Updated: 5 y ago License: No License (No License)Support
Quality
Security
License
Reuse
P
Support
Quality
Security
License
Reuse
i
inverse_rlby ahq1993
Adversarial Imitation Via Variational Inverse Reinforcement Learning
Python 87Updated: 2 y ago License: Permissive (MIT)
87Updated: 2 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
c
clevr_robot_envby google-research
CLEVR-Robot: a reinforcement learning environment combining vision, language and control.
Python 87Updated: 4 y ago License: Permissive (Apache-2.0)
87Updated: 4 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
R
RLenv.directoryby pschydlo
Explore and find reinforcement learning environments in a list of 150+ open source environments.
JavaScript 87Updated: 3 y ago License: Strong Copyleft (GPL-3.0)
87Updated: 3 y ago License: Strong Copyleft (GPL-3.0)Support
Quality
Security
License
Reuse
R
Reinforcement-Learning-for-Tradingby nicknochnack
A walkthrough of using the gym-anytrading environment for reinforcement learning applications leveraging custom datasets.
Jupyter Notebook 87Updated: 2 y ago License: No License (No License)
87Updated: 2 y ago License: No License (No License)Support
Quality
Security
License
Reuse
a
auction-gymby amzn
AuctionGym is a simulation environment that enables reproducible evaluation of bandit and reinforcement learning methods for online advertising auctions.
Jupyter Notebook 87Updated: 2 y ago License: Permissive (Apache-2.0)
87Updated: 2 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
r
rl_ardroneby nav74neet
Autonomous Navigation of UAV using Reinforcement Learning algorithms.
Python 86Updated: 4 y ago License: No License (No License)
86Updated: 4 y ago License: No License (No License)Support
Quality
Security
License
Reuse
l
lb-foragingby semitable
Level-based Foraging (LBF): A multi-agent environment for RL
Python 86Updated: 2 y ago License: Permissive (MIT)
86Updated: 2 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
s
sarl_starby LeeKeyu
SARL*: Deep RL based human-aware navigation for mobile robot in crowded indoor environments implemented in ROS.
Python 86Updated: 2 y ago License: Permissive (MIT)
86Updated: 2 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
C
CARLby automl
Benchmarking RL generalization in an interpretable way.
Python 86Updated: 2 y ago License: Permissive (Apache-2.0)
86Updated: 2 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
m
mario-rl-tutorialby chris-chris
Reinforcement Learning Tutorial on Super Mario
Python 85Updated: 2 y ago License: Permissive (Apache-2.0)
85Updated: 2 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
G
Gym.NETby SciSharp
openai/gym's popular toolkit for developing and comparing reinforcement learning algorithms port to C#.
C# 85Updated: 2 y ago License: Permissive (Apache-2.0)
85Updated: 2 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
d
deepRLby stone8oy
deep reinforcement learning for personal research
C++ 85Updated: 4 y ago License: Permissive (MIT)
85Updated: 4 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
A
AILibby 222464
A large collection of mostly reinforcement learning agents.
C++ 85Updated: 4 y ago License: Proprietary (Proprietary)
85Updated: 4 y ago License: Proprietary (Proprietary)Support
Quality
Security
License
Reuse
a
astoolby hardmaru
Augmented environments with RL
Jupyter Notebook 85Updated: 4 y ago License: Proprietary (Proprietary)
85Updated: 4 y ago License: Proprietary (Proprietary)Support
Quality
Security
License
Reuse
g
gamewalletby UseKeyp
Shell 85Updated: 2 y ago License: Permissive (MIT)
85Updated: 2 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
T
TSP-GNNby machine-reasoning-ufrgs
Graph Neural Network architecture to solve the decision variant of the Traveling Salesperson Problem (is there a Hamiltonian tour in G with up to a given cost?)
Python 84Updated: 2 y ago License: No License (No License)
84Updated: 2 y ago License: No License (No License)Support
Quality
Security
License
Reuse
R
Run-Skeleton-Runby Scitator
Reason8.ai PyTorch solution for NIPS RL 2017 challenge
Python 84Updated: 4 y ago License: Permissive (MIT)
84Updated: 4 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
R
RL-CBFby rcheng805
Python 84Updated: 2 y ago License: No License (No License)
84Updated: 2 y ago License: No License (No License)Support
Quality
Security
License
Reuse
s
simple-A2C-PPOby rgilman33
Actor-critic trained w PPO on OpenAI's Procgen Benchmark (PyTorch). Built from scratch.
Jupyter Notebook 84Updated: 4 y ago License: No License (No License)
84Updated: 4 y ago License: No License (No License)Support
Quality
Security
License
Reuse
R
Reinforcement_Learningby abhisheksuran
Deep Reinforcement Learning Algorithms implemented with Tensorflow 2.3
Jupyter Notebook 84Updated: 2 y ago License: No License (No License)
84Updated: 2 y ago License: No License (No License)Support
Quality
Security
License
Reuse
g
gym-continuousDoubleAuctionby ChuaCheowHuan
A custom MARL (multi-agent reinforcement learning) environment where multiple agents trade against one another (self-play) in a zero-sum continuous double auction. Ray [RLlib] is used for training.
Jupyter Notebook 84Updated: 3 y ago License: Permissive (MIT)
84Updated: 3 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
M
Minecraft-AIby drkostas
A Reinforcement Learning agent that learns how to to solve maze missions in Minecraft.
Python 84Updated: 2 y ago License: Permissive (Apache-2.0)
84Updated: 2 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
s
sc2aibotby pekaalto
Implementing reinforcement-learning algorithms for pysc2 -environment
Python 83Updated: 4 y ago License: No License (No License)
83Updated: 4 y ago License: No License (No License)Support
Quality
Security
License
Reuse
l
learning-to-drive-in-a-dayby r7vme
Implementation of reinforcement learning approach to make a car learn to drive
Python 83Updated: 4 y ago License: Permissive (MIT)
83Updated: 4 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
D
DoorGymby PSVL
Open source domain randomized door opening training environment
Python 83Updated: 2 y ago License: Proprietary (Proprietary)
83Updated: 2 y ago License: Proprietary (Proprietary)Support
Quality
Security
License
Reuse
S
Soft-Moduleby RchalYang
Code for "Multi-task Reinforcement Learning with Soft Modularization"
Python 83Updated: 2 y ago License: No License (No License)
83Updated: 2 y ago License: No License (No License)Support
Quality
Security
License
Reuse
P
PanelMatchby insongkim
R 83Updated: 2 y ago License: No License (No License)
83Updated: 2 y ago License: No License (No License)Support
Quality
Security
License
Reuse
r
relaby facebookresearch
Reinforcement Learning Assembly
C++ 83Updated: 4 y ago License: Permissive (MIT)
83Updated: 4 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
R
RLGCby RLGC-Project
An open-source platform for applying Reinforcement Learning for Grid Control (RLGC)
Jupyter Notebook 83Updated: 2 y ago License: Proprietary (Proprietary)
83Updated: 2 y ago License: Proprietary (Proprietary)Support
Quality
Security
License
Reuse
B
BinPacking_Neural_Combinatorial_Optimizationby rubensolozabal
Bin Packing Problem using Neural Combinatorial Optimization.
Python 82Updated: 3 y ago License: Permissive (MIT)
82Updated: 3 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
r
rl-bot-footballby ChintanTrivedi
An RL agent for the Google Football environment
Python 82Updated: 2 y ago License: No License (No License)
82Updated: 2 y ago License: No License (No License)Support
Quality
Security
License
Reuse
r
reinforcement-learningby udacity
Reinforcement learning material, code and exercises for Udacity Nanodegree programs.
Jupyter Notebook 82Updated: 4 y ago License: Permissive (MIT)
82Updated: 4 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
m
memory-mazeby jurgisp
Evaluating long-term memory of reinforcement learning algorithms
Python 82Updated: 2 y ago License: Permissive (MIT)
82Updated: 2 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
M
Multi-Agent-Reinforcement-Learningby yangchen1997
PyTorch implements multi-agent reinforcement learning algorithms, including QMIX, Independent PPO, Centralized PPO, Grid Wise Control, Grid Wise Control+PPO, Grid Wise Control+DDPG.
Python 82Updated: 2 y ago License: Permissive (MIT)
82Updated: 2 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
A
AirGymby Kjell-K
AirSim with openAI gym and keras-rl integration for autonomous copter RL
Python 81Updated: 4 y ago License: Permissive (MIT)
81Updated: 4 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
T
Trading-Gymby mymusise
A Trading environment base on Gym
Python 81Updated: 2 y ago License: No License (No License)
81Updated: 2 y ago License: No License (No License)Support
Quality
Security
License
Reuse
m
mgailby itaicaspi
Model-Based Generative Adversarial Imitation Learning
Python 81Updated: 4 y ago License: No License (No License)
81Updated: 4 y ago License: No License (No License)Support
Quality
Security
License
Reuse
l
lf2gymby elvisyjlin
An OpenAI-gym-like environment for Little Fighter 2
Python 81Updated: 4 y ago License: Permissive (MIT)
81Updated: 4 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
w
weizz-fuzzerby andreafioraldi
C 81Updated: 4 y ago License: No License (No License)
81Updated: 4 y ago License: No License (No License)Support
Quality
Security
License
Reuse
A
Autonomous-Driftingby kanakkabara
Autonomous Drifting using Reinforcement Learning
Jupyter Notebook 81Updated: 4 y ago License: No License (No License)
81Updated: 4 y ago License: No License (No License)Support
Quality
Security
License
Reuse
y
yarllby arnomoonens
Combining deep learning and reinforcement learning.
Python 80Updated: 4 y ago License: Permissive (MIT)
80Updated: 4 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
P
POMOby yd-kwon
codes for the paper "POMO: Policy Optimization with Multiple Optima for Reinforcement Learning"
Python 80Updated: 2 y ago License: No License (No License)
80Updated: 2 y ago License: No License (No License)Support
Quality
Security
License
Reuse
A
A-introduction-to-reinforcement-learningby xubo92
RL library based on algorithms from the book <A-introduction-to-reinforcement-learning>
Python 80Updated: 4 y ago License: No License (No License)
80Updated: 4 y ago License: No License (No License)Support
Quality
Security
License
Reuse
N
Neural-Lyapunov-Controlby YaChienChang
Learning Lyapunov functions and control policies of nonlinear dynamical systems
Jupyter Notebook 80Updated: 2 y ago License: No License (No License)
80Updated: 2 y ago License: No License (No License)Support
Quality
Security
License
Reuse
g
gym-micrortsby vwxyzjn
The Reinforcement Learning environment for the popular Real-time Strategy game simulator μRTS
Python 79Updated: 3 y ago License: No License (No License)
79Updated: 3 y ago License: No License (No License)Support
Quality
Security
License
Reuse
m
megastepby andyljones
megastep helps you build 1-million FPS reinforcement learning environments on a single GPU
Python 79Updated: 4 y ago License: Permissive (MIT)
79Updated: 4 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
s
sunriseby pokaxpoka
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning
Python 79Updated: 4 y ago License: No License (No License)
79Updated: 4 y ago License: No License (No License)Support
Quality
Security
License
Reuse