reinforcement learning

系统管理员 2022-08-23 03:54 6阅读 0赞

we are supposed to be different,folks,and wen people look at us,believe in yourself.

开山之作

[Reinforcement Learning: An Introduction][Reinforcement Learning_ An Introduction]

[Deep Reinforcement Learning 基础知识（DQN方面）][Deep Reinforcement Learning _DQN]

[增强学习Reinforcement Learning经典算法梳理1：policy and value iteration][Reinforcement Learning_1_policy and value iteration]

[增强学习Reinforcement Learning经典算法梳理2：蒙特卡洛方法][Reinforcement Learning_2]

[增强学习Reinforcement Learning经典算法梳理3：TD方法][Reinforcement Learning_3_TD]

[DRL前沿之：Hierarchical Deep Reinforcement Learning][DRL_Hierarchical Deep Reinforcement Learning]

[A Painless Q-learning Tutorial (一个 Q-learning 算法的简明教程)][A Painless Q-learning Tutorial _ Q-learning]

http://blog.csdn.net/dark\_scope/article/details/8252969

[强化学习系列][Link 1]

[增强学习（一） ----- 基本概念][-----]

[增强学习（二）----- 马尔可夫决策过程MDP][----- _MDP]

[增强学习（三）----- MDP的动态规划解法][----- MDP]

[增强学习（四） ----- 蒙特卡罗方法(Monte Carlo Methods)][----- _Monte Carlo Methods]

[增强学习（五）----- 时间差分学习(Q learning, Sarsa learning)][----- _Q learning_ Sarsa learning]

[增强学习与马尔科夫决策过程][Link 2]

[Torch中的增强学习层][Torch]

[\[深度学习\]利用Keras深度学习框架和卷积神经网络玩FlappyBird][Keras_FlappyBird]

[FlappyBirdRL][]

[用Tensorflow基于Deep Q Learning DQN 玩Flappy Bird][Tensorflow_Deep Q Learning DQN _Flappy Bird]

[深度强化学习：基于像素的乒乓游戏][Link 3]

[深度增强学习方向论文整理][Link 4]

[Reinforcement Learning_ An Introduction]: http://webdocs.cs.ualberta.ca/~sutton/book/the-book.html
[Deep Reinforcement Learning _DQN]: http://blog.csdn.net/songrotek/article/details/50580904
[Reinforcement Learning_1_policy and value iteration]: http://blog.csdn.net/songrotek/article/details/51378582
[Reinforcement Learning_2]: http://blog.csdn.net/songrotek/article/details/51381873
[Reinforcement Learning_3_TD]: http://blog.csdn.net/songrotek/article/details/51382759
[DRL_Hierarchical Deep Reinforcement Learning]: http://blog.csdn.net/songrotek/article/details/51384752
[A Painless Q-learning Tutorial _ Q-learning]: http://blog.csdn.net/itplus/article/details/9361915
[Link 1]: http://www.algorithmdog.com/tag/%E5%BC%BA%E5%8C%96%E5%AD%A6%E4%B9%A0
[-----]: http://www.cnblogs.com/jinxulin/p/3511298.html
[----- _MDP]: http://www.cnblogs.com/jinxulin/p/3517377.html
[----- MDP]: http://www.cnblogs.com/jinxulin/p/3526542.html
[----- _Monte Carlo Methods]: http://www.cnblogs.com/jinxulin/p/3560737.html
[----- _Q learning_ Sarsa learning]: http://www.cnblogs.com/jinxulin/p/5116332.html
[Link 2]: http://blog.csdn.net/lanbing510/article/details/49912739
[Torch]: http://blog.csdn.net/shenxiaolu1984/article/details/51592320
[Keras_FlappyBird]: http://blog.csdn.net/BaiHuaXiu123/article/details/54572515
[FlappyBirdRL]: https://github.com/SarvagyaVaish/FlappyBirdRL
[Tensorflow_Deep Q Learning DQN _Flappy Bird]: http://blog.csdn.net/songrotek/article/details/50951537
[Link 3]: http://www.tuicool.com/articles/ieuIN3z
[Link 4]: http://geek.csdn.net/news/detail/126093