人工智能是21世纪最激动人心的技术之一。人工智能,就是像人一样的智能,而人的智能包括感知、决策和认知(从直觉到推理、规划、意识等)。其中,感知解决what,深度学习已经超越人类水平;决策解决how,强化学习在游戏和机器人等领域取得了一定效果;认知解决why,知识图谱、因果推理和持续学习等正在研究。强化学习,采用反馈学习的方式解决序贯决策问题,因此必然是通往通用人工智能的终极钥匙。
下面是一些强化学习方面的经验总结整理分享:
1. 视频(从入门到放弃)
1.1 腾讯_周沫凡_强化学习、教程、代码
- https://www.bilibili.com/video/av16921335?from=search&seid=7037144790835305588
- https://morvanzhou.github.io/
- https://github.com/AndyYue1893/Reinforcement-learning-with-tensorflow 1.2 DeepMind_David Silver_UCL深度强化学习课程(2015)、PPT、笔记及代码
- https://www.bilibili.com/video/av45357759?from=search&seid=7037144790835305588
- https://blog.csdn.net/u_say2what/article/details/89216190
- https://zhuanlan.zhihu.com/p/37690204 1.3 台大_李宏毅_深度强化学习(国语)课程(2018)、PPT、笔记
- https://www.bilibili.com/video/av24724071?from=search&seid=7037144790835305588
- http://speech.ee.ntu.edu.tw/~tlkagk/courses_MLDS18.html
- https://blog.csdn.net/cindy_1102/article/details/87904928 1.4 UC Berkeley_Sergey Levine_CS285(294)深度强化学习(2019)、PPT、代码
- https://www.bilibili.com/video/av69455099?from=search&seid=7037144790835305588
- http://rail.eecs.berkeley.edu/deeprlcourse/
- https://github.com/berkeleydeeprlcourse/homework
2. 书籍
2.1 强化学习圣经_Rich Sutton_中文书、英文电子书、代码 ★★★★★(基础必读,有助于理解强化学习精髓)
- https://item.jd.com/12696004.html
- http://incompleteideas.net/book/the-book-2nd.html
- https://github.com/AndyYue1893/reinforcement-learning-an-introduction
2.2 Python强化学习实战_Sudharsan Ravichandiran、代码 ★★★★★(上手快,代码清晰)
- https://item.jd.com/12506442.html
- https://github.com/AndyYue1893/Hands-On-Reinforcement-Learning-With-Python
2.3 强化学习精要_冯超 ★★★★(从基础到前沿,附代码)
- https://item.jd.com/12344157.html
2.4 Reinforcement Learning With Open AI TensorFlow and Keras Using Python_OpenAI(注重实战)
- https://pan.baidu.com/share/init?surl=nQpNbhkI-3WucSD0Mk7Qcg(提取码: av5p)
3. 教程
3.1 OpenAI Spinning Up英文版、中文版、介绍by量子位(在线学习平台,包括原理、算法、论文、代码)
- https://spinningup.openai.com/en/latest/
- https://spinningup.readthedocs.io/zh_CN/latest/index.html
- https://zhuanlan.zhihu.com/p/49087870
3.2 莫烦Python( 通俗易懂)
- https://morvanzhou.github.io/
4. PPT
4.1 Reinforcement learning_Nando de Freitas_DeepMind_2019
- https://pan.baidu.com/s/1KF10W9GifZCDf9T4FY2H9Q
4.2 Policy Optimization_Pieter Abbeel_OpenAI/UC Berkeley/Gradescope - https://pan.baidu.com/s/1zOOZjvTAL_FRVTHHapriRw&shfl=sharepset
5. 算法
请问DeepMind和OpenAI身后的两大RL流派有什么具体的区别?
- https://www.zhihu.com/question/316626294/answer/627373838 三大经典算法
5.1 DQN
-
Mnih. Volodymyr, et al. “Human-level control through deep reinforcement learning.” Nature 518.7540 (2015): 529. (Nature版本)
-
https://storage.googleapis.com/deepmind-data/assets/papers/DeepMindNature14236Paper.pdf
5.2 DDPG
- David. Silver, et al. “Deterministic policy gradient algorithms.” ICML. 2014.
- http://proceedings.mlr.press/v32/silver14.pdf
5.3 A3C
- Mnih. Volodymyr, et al. “Asynchronous methods for deep reinforcement learning.” International conference on machine learning. 2016.
- https://www.researchgate.net/publication/301847678_Asynchronous_Methods_for_Deep_Reinforcement_Learning
6. 环境
6.1 OpenAI Gym
- http://gym.openai.com/
6.2 Google Dopamine 2.0
- https://github.com/google/dopamine
6.3 Emo Todorov Mujoco
- http://www.mujoco.org/
6.4 通用格子世界环境类
- https://zhuanlan.zhihu.com/p/28109312
- https://cs.stanford.edu/people/karpathy/reinforcejs/index.html
7. 框架
7.1 OpenAI Baselines(代码简洁,使用广泛)
- https://github.com/openai/baselines
7.2 百度 PARL( 扩展性强,可复现性好,友好)
- https://github.com/paddlepaddle/parl
7.3 DeepMind OpenSpiel(仅支持Debian和Ubuntu,28种棋牌类游戏和24种算法)
- https://github.com/deepmind/open_spiel
8. 论文
8.1 清华张楚珩博士 ★★★★★[2]
- https://zhuanlan.zhihu.com/p/46600521 张楚珩:强化学习论文汇总
8.2 NeuronDance ★★★★
- https://github.com/AndyYue1893/DeepRL-1/tree/master/A-Guide-Resource-For-DeepRL
8.3 paperswithcode ★★★★
- https://www.paperswithcode.com/area/playing-games
- https://github.com/AndyYue1893/pwc
8.4 Spinning Up推荐论文 ★★★★★
- https://zhuanlan.zhihu.com/p/50343077
9. 会议&期刊
9.1 会议:AAAI、NIPS、ICML、ICLR、IJCAI、 AAMAS、IROS等
9.2 期刊:AI、 JMLR、JAIR、 Machine Learning、JAAMAS等
9.3 计算机和人工智能会议(期刊)排名
- https://www.ccf.org.cn/xspj/rgzn/
- https://mp.weixin.qq.com/s?__biz=Mzg4MDE3OTA5NA==&mid=2247490957&idx=1&sn=b9aa515f7833ba1503be298ac2360960&source=41#wechat_redirect
- https://www.aminer.cn/ranks/conf/artificial-intelligence-and-pattern-recognition
10. 公众号
10.1 深度强化学习实验室 ★★★★★
10.2 深度学习技术前沿 ★★★★
10.3 AI科技评论 ★★★★
10.4 新智元 ★★★
11.知乎
11.1 用户
- 许铁-巡洋舰科技(微信公众号同名)、Flood Sung(GitHub同名)
- 田渊栋、周博磊、俞扬、张楚珩、天津包子馅儿、JQWang2048 及其互相关注大牛等
11.2 专栏
- David Silver强化学习公开课中文讲解及实践(叶强,很经典)
- 强化学习知识大讲堂(《深入浅出强化学习:原理入门》作者天津包子馅儿)
- 智能单元(杜克、Floodsung、wxam,聚焦通用人工智能,Flood Sung:深度学习论文阅读路线图 Deep Learning Papers Reading Roadmap很棒)
- 深度强化学习落地方法论(西交 大牛,实操经验丰富)
- 深度强化学习(知乎:JQWang2048,GitHub:NeuronDance,CSDN:- J. Q. Wang)
- 神经网络与强化学习(《Reinforcement Learning: An Introduction》读书笔记)
- 强化学习基础David Silver笔记(陈雄辉,南大,DiDi AI Labs)
12. 博客
12.1 草帽BOY
- https://blog.csdn.net/u013236946/category_6965927.html
12.2 J. Q. Wang
- https://blog.csdn.net/gsww404
12.3 Mr.Jk.Zhang
- https://blog.csdn.net/mrjkzhangma
12.4 Keavnn
- https://stepneverstop.github.io/
13. 官网
13.1 OpenAI
- https://www.openai.com/
13.2 DeepMind
- https://www.deepmind.com/
13.3 Berkeley
- https://bair.berkeley.edu/blog/?refresh=1