【专知荟萃23】深度强化学习RL知识资料全集（入门/进阶/论文/综述/代码/专家，附查看）

原创 2017-11-28 专知内容组 专知

点击上方“专知”关注获取专业AI知识!

【导读】主题荟萃知识是专知的核心功能之一，为用户提供AI领域系统性的知识学习服务。主题荟萃为用户提供全网关于该主题的精华（Awesome）知识资料收录整理，使得AI从业者便捷学习和解决工作问题！在专知人工智能主题知识树基础上，主题荟萃由专业人工编辑和算法工具辅助协作完成，并保持动态更新！另外欢迎对此创作主题荟萃感兴趣的同学，请加入我们专知AI创作者计划，共创共赢！专知为大家呈送专知主题荟萃知识资料大全集荟萃 （入门/进阶/综述/视频/代码/专家等），请大家查看！专知访问www.zhuanzhi.ai, 或关注微信公众号后台回复" 专知"进入专知，搜索感兴趣主题查看。此外，我们也提供该文网页桌面手机端（www.zhuanzhi.ai）完整访问，可直接点击访问收录链接地址，以及pdf版下载链接，请文章末尾查看！此为初始版本，请大家指正补充，欢迎在后台留言！欢迎大家转发分享~

【AlphaGoZero核心技术】深度强化学习专知荟萃

【AlphaGoZero核心技术】深度强化学习专知荟萃

基础入门
进阶文章

Papers
Papers for NLP

Tutorials
中英文综述
视频教程
代码
博客
领域专家

基础入门

1.Reinforcement learning wiki
[https://en.wikipedia.org/wiki/Reinforcement_learning]

2.Deep Reinforcement Learning: Pong from Pixels
[http://karpathy.github.io/2016/05/31/rl/]

3.CS 294: Deep Reinforcement Learning
[http://rll.berkeley.edu/deeprlcourse/]

4.什么是强化学习？
[http://www.cnblogs.com/geniferology/p/what_is_reinforcement_learning.html]

5.强化学习系列之一:马尔科夫决策过程
[http://www.algorithmdog.com/%E5%BC%BA%E5%8C%96%E5%AD%A6%E4%B9%A0-%E9%A9%AC%E5%B0%94%E7%A7%91%E5%A4%AB%E5%86%B3%E7%AD%96%E8%BF%87%E7%A8%8B]

6.强化学习系列之三:模型无关的策略评价
[http://www.algorithmdog.com/reinforcement-learning-model-free-evalution]

7.强化学习系列之九:Deep Q Network (DQN)
[http://www.algorithmdog.com/drl]

8.【整理】强化学习与MDP
[http://www.cnblogs.com/mo-wang/p/4910855.html]

9.强化学习入门及其实现代码
[http://www.jianshu.com/p/165607eaa4f9]

10.David视频里所使用的讲义pdf
[https://pan.baidu.com/s/1nvqP7dB]

11.强化学习简介——南京大学俞扬
[https://www.jianguoyun.com/p/DVSE-5AQ5oLtBRiKmis]

12.DavidSilver? 关于深度确定策略梯度 DPG的论文
[http://www.jmlr.org/proceedings/papers/v32/silver14.pdf]

13.Nature 上关于深度 Q 网络 (DQN) 论文:"
[http://www.nature.com/articles/nature14236]

14.【教程实战】Google DeepMind David Silver《深度强化学习》公开课教程学习笔记以及实战代码完整版 [http://mp.weixin.qq.com/s/y1aa_nIimSv4wlprGFHR7g]

进阶文章

Papers

1.Mastering the Game of Go without Human Knowledge
[https://deepmind.com/documents/119/agz_unformatted_nature.pdf]

2.Mastering the game of Go with deep neural networks and tree search
[http://www.nature.com/nature/journal/v529/n7587/abs/nature16961.html]

3.Human level control with deep reinforcement learning
[http://www.nature.com/nature/journal/v518/n7540/full/nature14236.html]

4.Play Atari game with deep reinforcement learning
[https://www.cs.toronto.edu/%7Evmnih/docs/dqn.pdf]

5.Prioritized experience replay
[https://arxiv.org/pdf/1511.05952v2.pdf]

6.Dueling DQN
[https://arxiv.org/pdf/1511.06581v3.pdf]

7.Deep reinforcement learning with double Q Learning
[https://arxiv.org/abs/1509.06461 ]

8.Deep Q learning with NAF
[https://arxiv.org/pdf/1603.00748v1.pdf]

9.Deterministic policy gradient
[http://jmlr.org/proceedings/papers/v32/silver14.pdf]

10.Continuous control with deep reinforcement learning) (DDPG)
[https://arxiv.org/pdf/1509.02971v5.pdf]

11.Asynchronous Methods for Deep Reinforcement Learning
[https://arxiv.org/abs/1602.01783]

12.Policy distillation
[https://arxiv.org/abs/1511.06295]

13.Unifying Count-Based Exploration and Intrinsic Motivation
[https://arxiv.org/pdf/1606.01868v2.pdf]

14.Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models
[https://arxiv.org/pdf/1507.00814v3.pdf]

15.Action-Conditional Video Prediction using Deep Networks in Atari Games
[https://arxiv.org/pdf/1507.08750v2.pdf]

16."Control of Memory, Active Perception, and Action in Minecraft"
[https://web.eecs.umich.edu/~baveja/Papers/ICML2016.pdf]

17.PathNet
[https://arxiv.org/pdf/1701.08734.pdf]

Papers for NLP

1.Coarse-to-Fine Question Answering for Long Documents
[https://homes.cs.washington.edu/~eunsol/papers/acl17eunsol.pdf]

2.A Deep Reinforced Model for Abstractive Summarization
[https://arxiv.org/pdf/1705.04304.pdf]

3.Reinforcement Learning for Simultaneous Machine Translation
[https://www.umiacs.umd.edu/~jbg/docs/2014_emnlp_simtrans.pdf]

4.Dual Learning for Machine Translation
[https://papers.nips.cc/paper/6469-dual-learning-for-machine-translation.pdf]

5.Learning to Win by Reading Manuals in a Monte-Carlo Framework
[http://people.csail.mit.edu/regina/my_papers/civ11.pdf]

6.Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
[http://people.csail.mit.edu/regina/my_papers/civ11.pdf]

7.Deep Reinforcement Learning with a Natural Language Action Space
[http://www.aclweb.org/anthology/P16-1153]

8.Deep Reinforcement Learning for Dialogue Generation
[https://arxiv.org/pdf/1606.01541.pdf]

9.Reinforcement Learning for Mapping Instructions to Actions
[http://people.csail.mit.edu/branavan/papers/acl2009.pdf]

10.Language Understanding for Text-based Games using Deep Reinforcement Learning
[https://arxiv.org/pdf/1506.08941.pdf]

11.End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning
[https://arxiv.org/pdf/1606.01269v1.pdf]

12.End-to-End Reinforcement Learning of Dialogue Agents for Information Access
[https://arxiv.org/pdf/1609.00777v1.pdf]

13.Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning
[https://arxiv.org/pdf/1702.03274.pdf]

14.Deep Reinforcement Learning for Mention-Ranking Coreference Models
[https://arxiv.org/abs/1609.08667]

Tutorials

Reinforcement Learning for NLP

[http://www.umiacs.umd.edu/~jbg/teaching/CSCI_7000/11a.pdf]

David Silver ICML2016 Tutorial: Deep Reinforcement Learning

[http://icml.cc/2016/tutorials/deep_rl_tutorial.pdf ]

David Silver ICML2016 Tutorial: Deep Reinforcement Learning 中文讲稿

[https://mp.weixin.qq.com/s/sq5_ZBoWpp9JOPaGkycKyg]

DQN tutorial

[https://medium.com/@awjuliani/simple-reinforcement-learning-with-tensorflow-part-4-deep-q-networks-and-beyond-8438a3e2b8df#.28wv34w3a]

强化学习简介——南京大学俞扬（PDF）

[https://www.jianguoyun.com/p/DVSE-5AQ5oLtBRiKmis]

中英文综述

深度强化学习综述：兼论计算机围棋的发展

[https://wenku.baidu.com/view/539025f99fc3d5bbfd0a79563c1ec5da50e2d684.html]

深度强化学习综述- 计算机学报

[https://wenku.baidu.com/view/772ea6e5ab00b52acfc789eb172ded630a1c9852.html]

深度强化学习综述：从AlphaGo背后的力量到学习资源分享| 机器之心

[https://zhuanlan.zhihu.com/p/25037206]

英文最新综述 DEEP REINFORCEMENT LEARNING: AN OVERVIEW

[https://arxiv.org/pdf/1701.07274.pdf]

视频教程

1.David Silver的这套视频公开课（Youtube）
[https://www.youtube.com/watch?v=2pWv7GOvuf0&ampampampampamplist=PL7-jPKtc4r78-wCZcQn5IqyuWhBZ8fOxT;]

2.David Silver的这套视频公开课（Youku）
[http://www.bilibili.com/video/av9831889/?from=search&seid=17387316110198388304?]

3.David Silver的这套视频公开课（Bilibili）
[http://www.bilibili.com/video/av9831889/?from=search&seid=17387316110198388304?]

4.强化学习课程 by David Silver
[https://www.bilibili.com/video/av8912293/?from=search&seid=1166472326542614796]

5.CS234: Reinforcement Learning
[http://web.stanford.edu/class/cs234/index.html]

6.什么是强化学习? (Reinforcement Learning)
[https://www.youtube.com/watch?v=NVWBs7b3oGk]

7.什么是 Q Learning (Reinforcement Learning 强化学习)
[https://www.youtube.com/watch?v=HTZ5xn12AL4]

8.Deep Reinforcement Learning
[http://videolectures.net/rldm2015_silver_reinforcement_learning/]

9.强化学习教程(莫烦)
[https://morvanzhou.github.io/tutorials/machine-learning/reinforcement-learning/]

10.David Silver ICML2016 Tutorial: Deep Reinforcement Learning 视频 [http://techtalks.tv/talks/deep-reinforcement-learning/62360/]

代码

1.OpenAI Gym
[https://github.com/openai/gym]

2.GoogleDeep Mind 团队深度 Q 网络 (DQN) 源码:
[http://sites.google.com/a/deepmind.com/dqn/]

3.ReinforcementLearningCode
[https://github.com/halleanwoo/ReinforcementLearningCode]

4.reinforcement-learning
[https://github.com/dennybritz/reinforcement-learning]

5.DQN
[https://github.com/devsisters/DQN-tensorflow]

6.DDPG
[https://github.com/stevenpjg/ddpg-aigym]

7.A3C01
[https://github.com/miyosuda/async_deep_reinforce]

8.A3C02
[https://github.com/openai/universe-starter-agent]

博客

1.Play pong with deep reinforcement learning based on pixel
[http://karpathy.github.io/2016/05/31/rl/]

2."What’s the Difference Between Artificial Intelligence, Machine Learning, and Deep Learning?"
[https://blogs.nvidia.com/blog/2016/07/29/whats-difference-artificial-intelligence-machine-learning-deep-learning-ai/]

3.Deep Learning in a Nutshell: Reinforcement Learning
[https://devblogs.nvidia.com/parallelforall/deep-learning-nutshell-reinforcement-learning/]

4.南京大学俞扬博士万字演讲全文：强化学习前沿
[https://www.leiphone.com/news/201705/NlTc7oObBqh116Z5.html]

5.Nature 上关于 AlphaGo 的论文 [http://www.nature.com/articles/nature16961]

6.AlphaGo 相关的资源 [https://deepmind.com/research/alphago/]

7.Reinforcement Learning(RL) for Natural Language Processing(NLP) [https://github.com/adityathakker/awesome-rl-nlp]