[强化学习]Part1:强化学习初印象
引入
智能
人工智能
强化学习初印象
强化学习的相关资料
- 经典书籍推荐:《Reinforcement Learning:An Introduction(强化学习导论)》(强化学习教父Richard Sutton 的经典教材)
- 经典理论课程推荐: 2015 David Silver经典强化学习公开课、 UC Berkeley CS285 、斯坦福 CS234
- 伯克利2018 Deep RL课程:http://rail.eecs.berkeley.edu/deeprlcourse/
- 强化学习经典论文
- DQN. "Playing atari with deep reinforcement learning." https://arxiv.org/pdf/1312.5602.pdf
- A3C. "Asynchronous methods for deep reinforcement learning." http://www.jmlr.org/proceedings/papers/v48/mniha16.pdf
- DDPG. "Continuous control with deep reinforcement learning." https://arxiv.org/pdf/1509.02971
- PPO. "Proximal policy optimization algorithms." https://arxiv.org/pdf/1707.06347
- 强化学习前沿研究方向:Model-base RL、 Hierarchical RL、 Multi Agent RL、 Meta Learning
- 经典环境库:GYM https://gym.openai.com/
- 框架库:PARL https://github.com/PaddlePaddle/PARL
说明
本系列文章,主要来自于百度飞桨深度学习学院的强化学习训练营课程以及个人整理的学习笔记。
课程大纲:
另外,该课程其它学员的笔记参考:
- https://zhuanlan.zhihu.com/p/149322765(作者:Tiny Tony,来自伯克利)
- https://blog.csdn.net/weixin_45623093/article/details/106822739(作者:三岁学编程)
- https://www.bilibili.com/video/BV1vZ4y1H7Sk?from=search&seid=549012863325744772(作者:nikankind)
- https://blog.csdn.net/qq_42067550/article/details/106844303(作者:AItrust)
- https://blog.csdn.net/qq_44635194/article/details/106812096(作者:烟笼寒水月笼沙)
- https://blog.csdn.net/zbp_12138/article/details/106800911(作者:Mr.郑先生_)
- https://yueqingsheng.github.io/post/qiang-hua-xue-xi-day-2-sarsa-q-learning/(作者:Goose)
( 说明:未经允许,禁止转载,望理解,谢谢)