we are supposed to be different,folks,and wen people look at us,believe in yourself.
开山之作
Reinforcement Learning: An Introduction
Deep Reinforcement Learning 基础知识(DQN方面)
增强学习Reinforcement Learning经典算法梳理1:policy and value iteration
增强学习Reinforcement Learning经典算法梳理2:蒙特卡洛方法
增强学习Reinforcement Learning经典算法梳理3:TD方法
DRL前沿之:Hierarchical Deep Reinforcement Learning
A Painless Q-learning Tutorial (一个 Q-learning 算法的简明教程)
http://blog.csdn.net/dark_scope/article/details/8252969
增强学习(四) ----- 蒙特卡罗方法(Monte Carlo Methods)
增强学习(五)----- 时间差分学习(Q learning, Sarsa learning)
[深度学习]利用Keras深度学习框架和卷积神经网络玩FlappyBird
用Tensorflow基于Deep Q Learning DQN 玩Flappy Bird
深度强化学习:基于像素的乒乓游戏