资料篇
课程
David Siver的公开课:
http://www0.cs.ucl.ac.uk/staff/D.Silver/web/Teaching.html
第一自然是David Silver的公开课,有一定接受门槛,习惯就好了。认真看完可以建立强化学习的知识体系。视频有点早,2015年的,所以还需要看看别的课程。
《Reinforcement Learning: An Introduction》
经典教材,结合David Silver的公开课一起看。
https://zhuanlan.zhihu.com/reinforce
对应的知乎中文公开课的解释。
https://github.com/dennybritz/reinforcement-learning
公开课对应的源码实现,不得不说代码比算法流程容易理解多了,既可以用来理解算法,也可以自己修改试玩。
http://web.stanford.edu/class/cs234/index.html
斯坦福的CS234
http://rll.berkeley.edu/deeprlcourse/
伯克利的公开课CS294
http://videolectures.net/deeplearning2016_pineau_reinforcement_learning/
从david silver的视频相关内容里发现的,还不错,只是没有字幕。
https://morvanzhou.github.io/tutorials/machine-learning/reinforcement-learning/
莫烦python,感觉特别傻瓜式。
大牛和实验室的主页
http://www0.cs.ucl.ac.uk/staff/d.silver/web/Home.html
https://deepmind.com/research/publications/
https://people.eecs.berkeley.edu/~pabbeel/
http://bair.berkeley.edu/blog/?refresh=1
很值得一看的博客
https://cs.stanford.edu/people/karpathy/reinforcejs/index.html
https://qqiang00.github.io/reinforce/javascript/demo_iteration.html
做动态规划的小demo
https://zhuanlan.zhihu.com/ikerpeng
深度强化学习基础
https://www.leiphone.com/news/201705/uO8nd09EnR77NBRP.html
南京大学俞扬博士:强化学习前沿
http://www.algorithmdog.com/drl
强化学习基础理论的系列文章
https://zhuanlan.zhihu.com/p/21369441
深度增强学习暑期学校 PPT 详解
https://zhuanlan.zhihu.com/sharerl
强化学习知识大讲堂
https://blog.csdn.net/Uwr44UOuQcNsUQb60zk2/article/details/78556998
深度强化学习入门:用TensorFlow构建你的第一个游戏AI
https://www.zhihu.com/question/57159315/answer/164323983
强化学习中on-policy 与off-policy有什么区别?
https://blog.csdn.net/u013236946/article/details/73243310
深度强化学习——连续动作控制DDPG、NAF
NAF挺有意思
https://zhuanlan.zhihu.com/p/27388383
基本model free 算法.
https://ai.intel.com/demystifying-deep-reinforcement-learning/
Demystifying Deep Reinforcement Learning
http://pemami4911.github.io/blog/2016/08/21/ddpg-rl.html
DDPG很好的博客的实现
http://karpathy.github.io/2016/05/31/rl/
Deep Reinforcement Learning: Pong from Pixels
https://www.alexirpan.com/2018/02/14/rl-hard.html
Deep Reinforcement Learning Doesn't Work Yet
又名强化学习劝退文
Tutorials
https://icml.cc/Conferences/2017/Tutorials
https://icml.cc/Conferences/2016/index.html%3Fp=97.html
https://nips.cc/Conferences/2016/Schedule?type=Tutorial
https://nips.cc/Conferences/2017/Schedule?type=Tutorial
Github
https://github.com/yenchenlin/DeepLearningFlappyBird
FlappyBird的DQN实现,理解DQN很有帮助。
https://github.com/carpedm20/deep-rl-tensorflow
实现了不少论文的方法,不过有些还是in progress
https://github.com/ShangtongZhang/reinforcement-learning-an-introduction
经典教材《Reinforcement Learning: An Introduction》的分章节实现。
https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow
莫烦强化学习的代码,即全又简单。
https://github.com/rll/rllab
TRPO TNPG 感觉像是另一套理论了。
https://github.com/openai/baselines
openAi的baseline
https://github.com/floodsung/DDPG
DDPG不错的一个实现
https://github.com/yadrimz/option-critic
option-critic的实现,主要是用来理解算法思想。
https://github.com/reinforceio/tensorforce
TensorForce: A TensorFlow library for applied reinforcement learning
别人家的资料整理
https://github.com/aikorea/awesome-rl#lectures
https://github.com/tigerneil/awesome-deep-rl
https://zhuanlan.zhihu.com/p/34918639
AlphaGO(单独拿出来)
最好的解读是知乎上的问题:
https://www.zhihu.com/question/41176911
https://www.zhihu.com/question/66861459
看过的源码实现:
https://github.com/Rochester-NRT/RocAlphaGo
https://github.com/junxiaosong/AlphaZero_Gomoku
https://github.com/yhyu13/AlphaGOZero-python-tensorflow
开源库:
https://github.com/tensorforce/tensorforce
https://github.com/rll/rllab
https://github.com/deepmind/trfl
https://github.com/google/dopamine
https://github.com/openai/baselines
https://github.com/astooke/rlpyt
https://github.com/p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch