A toolkit for developing and comparing reinforcement learning algorithms.
Support
Quality
Security
License
Reuse
r
reinforcement-learningby dennybritz
Jupyter Notebook 
19101
Version:Current
License: Permissive (MIT)
Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
Support
Quality
Security
License
Reuse
The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
Support
Quality
Security
License
Reuse
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
Support
Quality
Security
License
Reuse
An educational resource to help anyone learn deep reinforcement learning.
Support
Quality
Security
License
Reuse
R
Reinforcement-learning-with-tensorflowby MorvanZhou
Python 
8122
Version:Current
License: Permissive (MIT)
Simple Reinforcement learning tutorials, 莫烦Python 中文AI教学
Support
Quality
Security
License
Reuse
<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.
Support
Quality
Security
License
Reuse
强化学习中文教程(蘑菇书),在线阅读地址:https://datawhalechina.github.io/easy-rl/
Support
Quality
Security
License
Reuse
An elegant PyTorch deep reinforcement learning library.
Support
Quality
Security
License
Reuse
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
Support
Quality
Security
License
Reuse
(⌐■_■) - Deep Reinforcement Learning instrumenting bettercap for WiFi pwning.
Support
Quality
Security
License
Reuse
P
Practical_RLby yandexdataschool
Jupyter Notebook 
5328
Version:Current
License: Permissive (Unlicense)
A course in reinforcement learning in the wild
Support
Quality
Security
License
Reuse
D
Python 
4954
Version:Current
License: Permissive (MIT)
PyTorch implementations of deep reinforcement learning algorithms and environments
Support
Quality
Security
License
Reuse
d
deep-reinforcement-learningby udacity
Jupyter Notebook 
4487
Version:Current
License: Permissive (MIT)
Repo for the Deep Reinforcement Learning Nanodegree program
Support
Quality
Security
License
Reuse
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
Support
Quality
Security
License
Reuse
D
Deep_reinforcement_learning_Courseby simoninithomas
Jupyter Notebook 
3598
Version:Current
License: No License (No License)
Implementations from the free course Deep Reinforcement Learning with Tensorflow and PyTorch
Support
Quality
Security
License
Reuse
A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)
Support
Quality
Security
License
Reuse
[ICML 2021] DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning | 斗地主AI
Support
Quality
Security
License
Reuse
Tensorforce: a TensorFlow library for applied reinforcement learning
Support
Quality
Security
License
Reuse
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
Support
Quality
Security
License
Reuse
DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
Support
Quality
Security
License
Reuse
ELF: a platform for game research with AlphaGoZero/AlphaZero reimplementation
Support
Quality
Security
License
Reuse
Minimal and Clean Reinforcement Learning Examples
Support
Quality
Security
License
Reuse
TensorFlow Reinforcement Learning
Support
Quality
Security
License
Reuse
A library of reinforcement learning components and agents
Support
Quality
Security
License
Reuse
PyTorch0.4 implementation of: actor critic / proximal policy optimization / acer / ddpg / twin dueling ddpg / soft actor critic / generative adversarial imitation learning / hindsight experience replay
Support
Quality
Security
License
Reuse
An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)
Support
Quality
Security
License
Reuse
A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
Support
Quality
Security
License
Reuse
Modularized Implementation of Deep RL Algorithms in PyTorch
Support
Quality
Security
License
Reuse
D
Deep-reinforcement-learning-with-pytorchby sweetice
Python 
2907
Version:Current
License: Permissive (MIT)
PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....
Support
Quality
Security
License
Reuse
Massively Parallel Deep Reinforcement Learning. 🔥
Support
Quality
Security
License
Reuse
rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.
Support
Quality
Security
License
Reuse
Pytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchical RL
Support
Quality
Security
License
Reuse
OpenDILab Decision AI Engine
Support
Quality
Security
License
Reuse
TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
Support
Quality
Security
License
Reuse
Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
Support
Quality
Security
License
Reuse
Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
Support
Quality
Security
License
Reuse
ICCV2019 - Learning to Paint With Model-based Deep Reinforcement Learning
Support
Quality
Security
License
Reuse
Collection of reinforcement learning algorithms
Support
Quality
Security
License
Reuse
MuZero
Support
Quality
Security
License
Reuse
Reinforcement Learning in PyTorch
Support
Quality
Security
License
Reuse
An End-To-End, Lightweight and Flexible Platform for Game Research
Support
Quality
Security
License
Reuse
D
DeepReinforcementLearningby AppliedDataSciencePartners
Jupyter Notebook 
1965
Version:Current
License: Strong Copyleft (GPL-3.0)
A replica of the AlphaZero methodology for deep reinforcement learning in Python
Support
Quality
Security
License
Reuse
Motion imitation with deep reinforcement learning.
Support
Quality
Security
License
Reuse
A
Arcade-Learning-Environmentby mgbellemare
C++ 
1932
Version:Current
License: Strong Copyleft (GPL-2.0)
The Arcade Learning Environment (ALE) -- a platform for AI research.
Support
Quality
Security
License
Reuse
Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"
Support
Quality
Security
License
Reuse
A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities
Support
Quality
Security
License
Reuse
Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
Support
Quality
Security
License
Reuse
A minimalist environment for decision-making in autonomous driving
Support
Quality
Security
License
Reuse
The most simple, flexible, and comprehensive OpenAI Gym trading environment (Approved by OpenAI Gym)
Support
Quality
Security
License
Reuse
g
gymby openai
A toolkit for developing and comparing reinforcement learning algorithms.
Python
32193
Updated: 4 mo ago
License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
r
reinforcement-learningby dennybritz
Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
Jupyter Notebook
19101
Updated: 4 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
m
ml-agentsby Unity-Technologies
The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
C#
14917
Updated: 4 mo ago
License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
A
AirSimby microsoft
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
C++
14562
Updated: 4 mo ago
License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
s
spinningupby openai
An educational resource to help anyone learn deep reinforcement learning.
Python
8539
Updated: 4 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
R
Reinforcement-learning-with-tensorflowby MorvanZhou
Simple Reinforcement learning tutorials, 莫烦Python 中文AI教学
Python
8122
Updated: 4 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
S
SuperAGIby TransformerOptimus
<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.
Python
7659
Updated: 4 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
e
easy-rlby datawhalechina
强化学习中文教程(蘑菇书),在线阅读地址:https://datawhalechina.github.io/easy-rl/
Jupyter Notebook
6574
Updated: 4 mo ago
License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
t
tianshouby thu-ml
An elegant PyTorch deep reinforcement learning library.
Python
6356
Updated: 4 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
s
stable-baselines3by DLR-RM
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
Python
5890
Updated: 4 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
p
pwnagotchiby evilsocket
(⌐■_■) - Deep Reinforcement Learning instrumenting bettercap for WiFi pwning.
JavaScript
5889
Updated: 4 mo ago
License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
P
Practical_RLby yandexdataschool
A course in reinforcement learning in the wild
Jupyter Notebook
5328
Updated: 5 mo ago
License: Permissive (Unlicense)
Support
Quality
Security
License
Reuse
D
Deep-Reinforcement-Learning-Algorithms-with-PyTorchby p-christ
PyTorch implementations of deep reinforcement learning algorithms and environments
Python
4954
Updated: 4 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
d
deep-reinforcement-learningby udacity
Repo for the Deep Reinforcement Learning Nanodegree program
Jupyter Notebook
4487
Updated: 5 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
o
open_spielby deepmind
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
C++
3671
Updated: 5 mo ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
D
Deep_reinforcement_learning_Courseby simoninithomas
Implementations from the free course Deep Reinforcement Learning with Tensorflow and PyTorch
Jupyter Notebook
3598
Updated: 4 mo ago
License: No License (No License)
Support
Quality
Security
License
Reuse
R
ReAgentby facebookresearch
A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)
Python
3396
Updated: 4 mo ago
License: Permissive (BSD-3-Clause)
Support
Quality
Security
License
Reuse
D
DouZeroby kwai
[ICML 2021] DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning | 斗地主AI
Python
3321
Updated: 4 mo ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
t
tensorforceby tensorforce
Tensorforce: a TensorFlow library for applied reinforcement learning
Python
3230
Updated: 7 mo ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
p
pytorch-a2c-ppo-acktr-gailby ikostrikov
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
Python
3217
Updated: 4 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
d
dm_controlby deepmind
DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
Python
3201
Updated: 4 mo ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
E
ELFby pytorch
ELF: a platform for game research with AlphaGoZero/AlphaZero reimplementation
C++
3172
Updated: 2 y ago
License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
r
reinforcement-learningby rlcode
Minimal and Clean Reinforcement Learning Examples
Python
3150
Updated: 5 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
t
trflby deepmind
TensorFlow Reinforcement Learning
Python
3136
Updated: 10 mo ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
a
acmeby deepmind
A library of reinforcement learning components and agents
Python
3103
Updated: 5 mo ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
R
RL-Adventure-2by higgsfield
PyTorch0.4 implementation of: actor critic / proximal policy optimization / acer / ddpg / twin dueling ddpg / soft actor critic / generative adversarial imitation learning / hindsight experience replay
Jupyter Notebook
2994
Updated: 5 mo ago
License: No License (No License)
Support
Quality
Security
License
Reuse
A
AlphaZero_Gomokuby junxiaosong
An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)
Python
2953
Updated: 4 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
G
Gymnasiumby Farama-Foundation
A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
Python
2947
Updated: 4 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
D
DeepRLby ShangtongZhang
Modularized Implementation of Deep RL Algorithms in PyTorch
Python
2938
Updated: 5 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
D
Deep-reinforcement-learning-with-pytorchby sweetice
PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....
Python
2907
Updated: 4 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
E
ElegantRLby AI4Finance-Foundation
Massively Parallel Deep Reinforcement Learning. 🔥
Python
2902
Updated: 4 mo ago
License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
r
rllabby rll
rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.
Python
2784
Updated: 5 mo ago
License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
R
RL-Adventureby higgsfield
Pytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchical RL
Jupyter Notebook
2747
Updated: 8 mo ago
License: No License (No License)
Support
Quality
Security
License
Reuse
D
DI-engineby opendilab
OpenDILab Decision AI Engine
Python
2614
Updated: 4 mo ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
a
agentsby tensorflow
TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
Python
2508
Updated: 5 mo ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
m
minimalRLby seungeunrho
Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
Python
2468
Updated: 4 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
c
coachby IntelLabs
Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
Python
2248
Updated: 5 mo ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
I
ICCV2019-LearningToPaintby megvii-research
ICCV2019 - Learning to Paint With Model-based Deep Reinforcement Learning
Python
2190
Updated: 6 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
r
rlkitby rail-berkeley
Collection of reinforcement learning algorithms
Python
2148
Updated: 5 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
m
Support
Quality
Security
License
Reuse
r
rlpytby astooke
Reinforcement Learning in PyTorch
Python
2096
Updated: 8 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
E
ELFby facebookresearch
An End-To-End, Lightweight and Flexible Platform for Game Research
C++
2085
Updated: 8 mo ago
License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
D
DeepReinforcementLearningby AppliedDataSciencePartners
A replica of the AlphaZero methodology for deep reinforcement learning in Python
Jupyter Notebook
1965
Updated: 8 mo ago
License: Strong Copyleft (GPL-3.0)
Support
Quality
Security
License
Reuse
D
DeepMimicby xbpeng
Motion imitation with deep reinforcement learning.
C++
1948
Updated: 10 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
A
Arcade-Learning-Environmentby mgbellemare
The Arcade Learning Environment (ALE) -- a platform for AI research.
C++
1932
Updated: 5 mo ago
License: Strong Copyleft (GPL-2.0)
Support
Quality
Security
License
Reuse
m
multiagent-particle-envsby openai
Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"
Python
1868
Updated: 4 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
P
PettingZooby Farama-Foundation
A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities
Python
1857
Updated: 4 mo ago
License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
c
coachby NervanaSystems
Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
Python
1812
Updated: 3 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
h
highway-envby eleurent
A minimalist environment for decision-making in autonomous driving
Python
1706
Updated: 7 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
g
gym-anytradingby AminHP
The most simple, flexible, and comprehensive OpenAI Gym trading environment (Approved by OpenAI Gym)
Python
1656
Updated: 4 mo ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse