DRL
Posted nan0121
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了DRL相关的知识,希望对你有一定的参考价值。
1.Book
https://blog.floydhub.com/best-deep-learning-books-updated-for-2019/
grokking-deep-reinforcement-learning
https://livebook.manning.com/book/grokking-deep-reinforcement-learning/welcome/v-14/2
https://livebook.manning.com/book/deep-reinforcement-learning-in-action/chapter-5/59
2.Code
https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/blob/master/contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG.py
https://keras.io/examples/rl/ddpg_pendulum/
https://github.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On
https://github.com/mimoralea/gdrl
https://github.com/openai/spinningup
https://github.com/higgsfield/RL-Adventure-2
https://github.com/pemami4911/deep-rl
3.Course
https://blog.floydhub.com/best-deep-learning-courses-updated-for-2019/#spinning-up
https://cn.udacity.com/course/deep-reinforcement-learning-nanodegree--nd893-cn
4.Link
https://github.com/openai/spinningup/blob/master/docs/spinningup/keypapers.rst
https://github.com/tensorflow/agents
5.understanding priority replay buffer
https://danieltakeshi.github.io/2019/07/14/per/
6.sumtree
https://jaromiru.com/2016/11/07/lets-make-a-dqn-double-learning-and-prioritized-experience-replay/
7.spinningup DDPG
https://spinningup.openai.com/en/latest/algorithms/ddpg.html
8.average DQN
https://zhuanlan.zhihu.com/p/74305734
9.deep learning drizzle
https://github.com/kmario23/deep-learning-drizzle#balloon-reinforcement-learning-hotsprings-video_game
10.blogs
https://morvanzhou.github.io/tutorials/machine-learning/reinforcement-learning/6-2-DDPG/
https://www.cnblogs.com/charlotte77/p/10311255.html
11.tutorial:
https://morvanzhou.github.io/tutorials/machine-learning/reinforcement-learning/
12.slide
以上是关于DRL的主要内容,如果未能解决你的问题,请参考以下文章
为啥缓存的 Drools KIE 基础仍然需要源 .drl 文件?
drools 中是不是有任何 API 可以通过传递值来动态创建 drl 文件?
DRL前沿之:Benchmarking Deep Reinforcement Learning for Continuous Control