「ML」 强化学习资料汇总
智能算法在没有人为指导的情况下,通过不断的试错来提升任务性能的过程;
reinforcement learning
1 综述
-
A Survey of Deep Reinforcement Learning in Video Games
2019-12-23 paper -
A Survey of Reinforcement Learning Techniques: Strategies, Recent Development, and Future Directions
2020-01-19 paper
2 理论
-
Revisiting the Softmax Bellman Operator: New Benefits and New Perspective
ICML 2019 2018-12-02 paper -
Maximum Entropy-Regularized Multi-Goal Reinforcement Learning
ICML 2019 2019-05-21 paper
3 其他
-
Meta-Gradient Reinforcement Learning
2018-05-24 Paper -
A Survey on Transfer Learning for Multiagent Reinforcement Learning Systems
-
Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications
2018-12-31 Paper -
Learning 3D Navigation Protocols on Touch Interfaces with Cooperative Multi-Agent Reinforcement Learning
2019-04-16 Paper
多代理合作的触摸屏 3D 导航协议;
附录
A 研究员
B 参考资料
1 书籍
- Richard S. Sutton, Andrew G. Barto. Reinforcement Learning:An Introduction[M].
主页 | python 实现 | stanford-pdf
2 课程
-
An Introduction to Reinforcement Learning
David Silver, Video-youtube | Video-Bilibili | lectures | python 实现 | google-drive-包括讲义和视频
3 博客
- 莫凡. 强化学习[EB/OL]. https://morvanzhou.github.io/tutorials/machine-learning/reinforcement-learning/. 2016-11-03/2019-04-19.
- 不会停的蜗牛. 一文了解强化学习[EB/OL]. https://www.jianshu.com/p/f4409a8b7f71. 2017-06-16/2019-04-19.
- JustFollowUs. Reinforcement-Learning[EB/OL]. https://github.com/JustFollowUs/Reinforcement-Learning. 2017-04-11/2019-04-19.
- 王小惟. 强化学习从入门到放弃的资料[EB/OL]. https://zhuanlan.zhihu.com/p/34918639. 2018-03-25/2019-04-22.
- ICLR 2018 总结
4 报告
RLDM 2019 笔记-David Abel
Comments