README.md

awesome-reinforcement-learning

强化学习的相关学习资源、链接

网址教程资源

教程网址

• 强化学习系列教程
• 强化学习知识大讲堂
• 南京大学俞扬博士万字演讲全文：强化学习前沿
• OpenAi Spinning Up
• David Silver《深度强化学习》公开课教程学习笔记以及实战

Book

• Hands-On Reinforcement Learning With Python
• Reinforcement Learning: Theory and Python Implementation
• An Introduction to Deep Reinforcement Learning
• Foundations and Trends® in Machine Learning
• REINFORCEMENT LEARNING AND OPTIMAL CONTROL

Video Course

• CS 294: Deep Reinforcement Learning；
  • 中文翻译-2018秋季CS294-112深度强化学习；
  • CS294课程中文笔记-1；
  • CS294课程中文笔记-2 (记录较好);
  • 作业讲解
• David Silver's course;
  • David视频里所使用的讲义pdf
• John Schulmann's lectures
• Deep RL Bootcamp
• CS 287: Advanced Robotics, Fall 2015
• CS234: Reinforcement Learning Winter 2019
• Deep Learning (DLSS) and Reinforcement Learning (RLSS) Summer School, Montreal 2017
• Advanced Deep Learning and Reinforcement Learning
• 强化学习教程(莫烦)

博客网址

• Play pong with deep reinforcement learning based on pixel
• Deep Learning in a Nutshell: Reinforcement Learning
• AlphaGo

领域专家

• 加州大学伯克利分校机器人学专家 Sergey Levine
• 前百度首席科学家 Andrew Ng
• 加拿大阿尔伯塔大学著名增强学习大师Richard S. Sutton 教授
• Google DeepMind AlphaGo项目的主程序员 David Silver 博士
• 机器博弈专家Tuomas Sandholm教授

Awesome

• Reinforcement learning resources curated
• Awesome Reinforcement Learning(RL) for Natural Language Processing(NLP))
• Paper list of multi-agent reinforcement learning (MARL) )
• A list of recent papers regarding deep reinforcement learning
• TensorFlow implementation of Deep Reinforcement Learning papers
• Deep Reinforcement Learning Papers
• Reinforcement learning resources curated
• This project is for learning and researching on Deep RL. Maintained by University AI researchers
• 强化学习从入门到放弃的资料
• Reinforcement Learning Notebooks
• Deep Reinforcement Learning(深度强化学习)

Algorithm Repos

• rllab
• Baseline
• Stable Baselines
• keras-rl
• BURLAP
• PyBrain
• RLPy
• A Matlab Toolbox for Approximate RL and DP

强化学习实战资源

Implementation of Algorithms

• Pytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchical RL
• PyTorch implementations of various DRL algorithms for both single agent and multi-agent
• Deep Reinforcement Learning for Keras
• PyTorch 实现 DQN, AC, A2C, A3C, , Policy Gradient, DDPG, TRPO, PPO, ACER
• Deep Reinforcement learning framework
• Codes for understanding Reinforcement Learning( updating... )
• Contains high quality implementations of Deep Reinforcement Learning algorithms written in PyTorch
• Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course
• Repo for the Deep Reinforcement Learning Nanodegree program
• 教程 | 如何在Unity环境中用强化学习训练Donkey Car
• 深入浅出解读"多巴胺（Dopamine）论文"、环境配置和实例分析

Project

• DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
  • [code];
  • SFV
• StarCraft II - pysc2 Deep Reinforcement Learning Examples
• An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)
• Using reinforcement learning to teach a car to avoid obstacles
• A reinforcement learning algorithm for the 2048 game

论文

• DQN-arxiv (Deep Q-Networks ): Mnih et al, 2013
  • DQN-nature(Deep Q-Network ); Mnih et al, 2015
  • Double DQN (Double Q Network) : Hasselt et al, 2015
  • Dueling DQN (Duling Q Network) : Ziyu Wang et al, 2015
  • QR-DQN (Quantile Regression DQN): Dabney et al, 2017
• Alpha Go(Mastering the game of Go with deep neural networks and tree search)
  • AlphaZero-arxiv (Mastering Chess and Shogi by Self-Play) :Silver et al, 2017
  • AlphaZero-nature (Go without human knowledge) :Silver et al, 2017
• SAC (Off-Policy Maximum Entropy): Haarnoja et al, 2018
  • SAC (Algorithms and Applications) : Haarnoja, et al 2018
• A2C / A3C (Asynchronous Advantage Actor-Critic): Mnih et al, 2016
• PPO (Proximal Policy Optimization): Schulman et al, 2017
• TRPO (Trust Region Policy Optimization): Schulman et al, 2015
• DPG (Deterministic Policy Gradient) : DavidSilver et al, 2014
• DDPG (Deep Deterministic Policy Gradient): Lillicrap et al, 2015
• TD3 (Twin Delayed DDPG): Fujimoto et al, 2018
• NAF (Normalized adantage functions) : ShixiangGu et al, 2016
• C51 (Categorical 51-Atom DQN): Bellemare et al, 2017
• HER (Hindsight Experience Replay): Andrychowicz et al, 2017
• World Models Ha and Schmidhuber, 2018
• I2A (Imagination-Augmented Agents): Weber et al, 2017
• MBMF (Model-Based RL with Model-Free Fine-Tuning): Nagabandi et al, 2017
• MBVE (Model-Based Value Expansion): Feinberg et al, 2018
• PathNet(Evolution Channels Gradient Descent): Fernando et al, 2017
• plannet(Learning Latent Dynamics) : Hafner, et al, 2018
• TCN (Time-Contrastive Networks):Sermanet, et al, 2017
• Reinforcement and Imitation Learning : Yuke Zhu†, et al 2018
• Prioritized experience replay:Schaul, et al 2015
• Policy distillation : Rusu, et al 2015
• Unifying Count-Based Exploration and Intrinsic Motivation : Bellemare, et al 2015
• Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models : Stadie, et al 2015
• Action-Conditional Video Prediction using Deep Networks in Atari Games : JunhyukOh, et al 2015
• Control of Memory, Active Perception, and Action in Minecraft : JunhyukOh, et al 2015