强化学习- Reinforcement Learning- 学习资源

主要收录整理的一些学习资源

首要资源链接-知乎：  https://zhuanlan.zhihu.com/p/35212427?group_id=964152225728258048 

UC Berkeley 课程：  http://rll.berkeley.edu/deeprlcourse/ 

FUll Source LInks：  http://www.jeremydjacksonphd.com/category/deep-learning/ 

知乎专栏： https://zhuanlan.zhihu.com/sharerl?author=guoxiansia 

知乎专栏1： https://zhuanlan.zhihu.com/intelligentunit 

某CSDN博客： https://blog.csdn.net/zhangweijiqn/article/details/53200204 

入门介绍： https://blog.csdn.net/beiergelaide/article/details/78061356

强化学习入门 ： https://blog.csdn.net/beiergelaide/article/details/78061356

Denny Britz 的 Website： http://www.wildml.com/2016/10/learning-reinforcement-learning/

Denny Britz Blog ：http://blog.dennybritz.com/

其他资料：

«Reinforcement learning in robotics: A survey»
«Reinforcement Learning in Robotics: Applications and Real-World Challenges»
«Policy Gradient Methods for Robotics»
«Extending the OpenAI Gym for robotics: a toolkit for reinforcement learning using ROS and Gazebo»

Deep Reinforcement Learning深度增强学习可以说发源于2013年DeepMind的Playing Atari with Deep Reinforcement Learning 一文，之后2015年DeepMind 在Nature上发表了Human Level Control through Deep Reinforcement Learning一文使Deep Reinforcement Learning得到了较广泛的关注，在2015年涌现了较多的Deep Reinforcement Learning的成果。而2016年，随着AlphaGo的出现，Deep Reinforcement Learning 将进入全面发展的阶段。

Deep Reinforcement Learning面向决策与控制问题，而决策与控制很大程度上决定了人工智能的发展水平。也因此，AlphaGo的出现具有里程碑的意义。Deep Reinforcement Learning研究使用深度神经网络来解决决策控制问题，是深度学习领域最前沿的研究方向之一。

本文主要收集与Deep Reinforcement Learning相关的各种资料，希望对有兴趣研究的童鞋有所帮助。接下来，本专栏将由我继续发布Deep Reinforcement Learning的相关文章。

PS：最新的资料会在资料前方标出。

1 学习资料

1）增强学习相关课程：

• David Silver的增强学习课程（有视频和ppt）: http://www0.cs.ucl.ac.uk/staff/D.Silver/web/Teaching.html
  
• 最好的增强学习教材：Sutton & Barto Book: Reinforcement Learning: AnIntroduction
  
• Nando de Freitas的深度学习课程 （有视频有ppt有作业）：Machine Learning
  
• Michael Littman的增强学习课程：https://www.udacity.com/course/reinforcement-learning–ud600
• Pieter Abbeel 的AI课程（包含增强学习，使用Pacman实验）：Artificial Intelligence
• Pieter Abbeel 的深度增强学习课程：CS 294 Deep Reinforcement Learning, Fall 2015
• Pieter Abbeel 的 高级机器人技术（Advanced Robotics）: CS287 Fall 2015
  
• 最新机器人专题课程Penn（2016年开课）：Specialization
  
• (最新）Deep Learning Summer School：pptsvideos

2）深度学习相关课程：

• Fei Fei Li的用于视觉识别的卷积神经网络 : CS231n Convolutional Neural Networks for Visual Recognition
  
• Andrew Ng（一个是Coursera上的课程，一个是Stanford的课程）：Machine LearningCS 229: Machine Learning
• Hinton的神经网络课程（Neural Network for Machine Learning)(2012年的）Coursera - Free Online Courses From Top Universities
  

3）深度增强学习相关blog：

• drl的入门博客（感谢知友Richard Huang）
  

1. Guest Post (Part I): Demystifying Deep Reinforcement Learning

2.Guest Post (Part II): Deep Reinforcement Learning with Neon

3.Blog Post (Part III): Deep Reinforcement Learning with OpenAI Gym

• Andrej Karpathy blog: Deep Reinforcement Learning: Pong from Pixels

2 深度增强学习相关讲座

• David Silver的：
  

ICLR 2015 part 1 https://www.youtube.com/watch?v=EX1CIVVkWdE

ICLR 2015 part 2 https://www.youtube.com/watch?v=zXa6UFLQCtg

UAI 2015 https://www.youtube.com/watch?v=qLaDWKd61Ig

RLDM 2015 Deep Reinforcement Learning

ICML 2016：深度增强学习TutorialAlphaGo Tutorial

• Pieter Abbeel: https://www.youtube.com/watch?v=evq4p1zhS7Q
• Sergey Levine: Deep Robotic Learning
• John Schulman：Machine Learning Summer School

3 论文资料

• GitHub - junhyukoh/deep-reinforcement-learning-papers: A list of recent papers regarding deep reinforcement learning
  
• GitHub - muupan/deep-reinforcement-learning-papers: A list of papers and resources dedicated to deep reinforcement learning
  

这两个人收集的基本涵盖了当前deep reinforcement learning 的论文资料。目前确实不多。

4 大牛与企业情况：

• DeepMind：http://www.deepmind.com/publications.html
• OpenAI: OpenAI Gym
• Pieter Abbeel 团队(已加入OpenAI）：Pieter Abbeel---Associate Professor UC Berkeley---Co-Founder Gradescope---
• Satinder Singh:Home page for Satinder Singh (Baveja) and Reinforcement Learning
• CMU 进展：Lerrel PintoRuslan Salakhutdinov
• Prefered Networks: (日本创业公司）Preferred Networks
  
• Osaro:www.osaro.com
  

5 会议情况

• NIPS 2015 Deep Reinforcement Learning Workshop
• ICLR 2016
• RSS 2016 Deep Learning for Robotics

6 开源代码

在github可以找到dqn，ddpg，a3c, trpo 等深度增强学习典型算法的代码，以下为一些举例的开源代码：

• GitHub - songrotek/DeepTerrainRL: terrain-adaptive locomotion skills using deep reinforcement learning
  
• GitHub - songrotek/async-rl: An attempt to reproduce the results of "Asynchronous Methods for Deep Reinforcement Learning" (http://arxiv.org/abs/1602.01783)
  
• GitHub - songrotek/rllab: rllab is a framework for developing and evaluating reinforcement learning algorithms.
  
• GitHub - songrotek/DRL-FlappyBird: Playing Flappy Bird Using Deep Reinforcement Learning (Based on Deep Q Learning DQN using Tensorflow)
  
• GitHub - songrotek/DeepMind-Atari-Deep-Q-Learner: The original code from the DeepMind article + my tweaks