RL-Gallery

• Framework
• Tutorials
• Platform
• Implementation
• Papers
• Applications
• Technique

RL Framework

• Spinning Up, OpenAI
• Rllab, Berkeley RL Lab
• Rllib, UC Berkeley’s RISE Lab, Ray Project
• Rlkit, Vitchyr Pong's Implementations
• Stable-baselines
• Baselines, OpenAI
• TensorForce
• Keras RL
• Dopamine, Google
• Coach, Intel
• PARL, Baidu
• torchrl, salmanazarr's implementations
• rlpack, liber145's implementations
• ChainerRL, based on Chainer
• SLM-Lab, Wah Loon Keng's implementations
• adeptRL, heronsystems
• autonomous-learning-library, Chris Nota's implementations
• rlgraph, RLgraph
• rllite, lite repository for RL

RL Tutorials

• Reinforcement Learning: An Introduction
• CS 294-112, UC Berkeley
• David Silver's courses
• Deep RL Bootcamp, UC Berkeley
• MIT 6.S094: Deep Learning for Self-Driving Cars 2018 Lecture 3 Notes: Deep Reinforcement Learning
• UCL Advanced Deep Learning & Reinforcement Learning
• CS234: Reinforcement Learning Winter 2019, Stanford
• awesome-deep-rl
• An Introduction to Deep Reinforcement Learning
• Morvan Reinforcement Learning
• PyTorch tutorials of RL
• Arthur Juliani's blog
• Thomas Simonini's DRL course
• Lilian Weng's blog
• Andrej Karpathy's blog
• Hung-yi Lee's DRL lectures (Chinese version)
• Spinning Up in Deep RL Workshop, OpenAI
• Reproducible, Reusable, and Robust RL, Joelle Pineau
• Udacity, RL by Georgia Tech
• Deep Learning Summer School, Montreal 2016
• CS 287: Advanced Robotics, Fall 2015
• RLKorea (Korean version)
• phd-bibliography

RL Platform

• Gym, OpenAI
• Universe, OpenAI
• Roboschool, OpenAI
• PlayGround: AI Research into Multi-Agent Learning
• Neural MMO: A Massively Multiagent Game Environment
• ELF, a platform for game research, Facebook
• Reaver, StarCraft II
• Pybullet: Real-Time Physics Simulation
• highway driving environments
• ma-gym
• multiworld, Vitchyr Pong

RL Implementation

• RL-Adventure, Dulat Yerzat's implementation
• RL-Adventure2, Dulat Yerzat's implementation
• John Schulman's RL repository
• TianhongDai's implementations
• Denny Britz's implementations
• steveKapturowski's implementations
• DeepRL, ShangtongZhang's implementations
• reinforcement-learning-an-introduction, ShangtongZhang's implementations
• Reinforcement-learning-with-tensorflow, Morvan Zhou's implementations
• mario_rl, Chanwoong joo's implementations
• PyTorch-RL, Ye Yuan's implementations
• pytorchrl, Ermo Wei's implementations
• Entropy-Regularized-RL, lihaoruo's implementations
• Tidy-Reinforcement-learning, sarcturus00's implementations
• Random Network Distillation, jcwleo's implementation
• rl-baselines-zoo, pre-trained RL agents using stable-baselines
• rl-agents, Edouard Leurent's implementations
• pytorch-rl, Navneet M Kumar's implementations
• lets-do-irl, Reinforcement Learning KR's implementations
• tensorflow_practice/rl, princewen's implementations
• self-imitation-learning, Junhyuk Oh's implementations
• pytorch-a2c-ppo-acktr-gail, Ilya Kostrikov's implementations
• Deep_RL_with_pytorch, sungyubkim's implementations
• pytorch-madrl, Chenglong Chen's implementations
• Deep-reinforcement-learning-with-pytorch, Johnny He's implementations
• Sam Greydanus's A3C implementation
• TD3 implementation
• SAC implementation
• simple-A2C, Rudy Gilman's implementations
• DeepPILCO, zuoxingdong's implementation
• FeUdal-montezuma, Woongwon Lee's implementations
• Tidy-Reinforcement-learning, sarcturus00's implementations
• learning-to-communicate-pytorch, Minqi's implementations
• pytorch-cpp-rl, Isaac Poulton's implementations
• deep-rl, Pedro Morais's implementations
• Inverse-Reinforcement-Learning, Matthew Alger's implementations
• ReinforcementLearning-AtariGame, Nasrudin Bin Salim's implementations
• RND-Pytorch, WizDom13's implementations
• Deep-Reinforcement-Learning-Algorithms-with-PyTorch, Petros Christodoulou's implementations
• reinforcement_learning, Yiren Lu's implementations
• rl_a3c_pytorch, David Griffis's implementations
• RL-Experiments, Yanhua Huang's implementations
• Hierarchical-Actor-Critc-HAC-, Andrew Levy's implementation
• tensorflow_RL, RLOpensource
• noreward-rl, Deepak Pathak's implementations
• robotics-rl-srl, Antonin RAFFIN's implementations
• Super-Mario-Bros-RL, Amine SADEQ's implementations
• rltf, Nikolay Nikolov's implementations
• reward-learning-rl, Avi Singh's implementation
• Deep-Reinforcement-Learning-Algorithms-with-PyTorch, Petros Christodoulou's implementations
• rl-starter-files, Lucas Willems's implementation
• rl_a3c_pytorch, David Griffis's implementation
• DRL, createamind's implementations
• lagom, Xingdong Zuo's implementations
• rltime, Opher Lieber's implementations
• rl_algorithms, Medipixel
• rlpyt, astooke's implementations

RL Papers

• Model-based-papers
• DRL papers 2015-2016, Junhyuk Oh
• DRL papers 2015-2016, Yasuhiro Fujita
• MARL-Papers
• Spinning up, OpenAI

RL Applications

• Play Atari games, DeepMind
• AlphaGo & AlphaGoZero, playing Go, DeepMind
• AlphaStar, playing StarCraft2, DeepMind
• Autonomous helicopter flight, Stanford University
• Skill learning in 3D simulator, Xue Bin Peng
• Agile locomotion for quadruped robots, Jie Tan
• ANYmal robot skill learning, Synced
• Modular legged robot skill learning, Disney Research
• RL in business (Chinese version), Alibaba
• LOXM, executing trades, J.P.Morgan

RL Technique

PS: "Mentioned Key Algorithm" may not be the first algorithm that uses this technique, but makes a detailed explanation