参考文献: 深度增强学习David Silver(二)——马尔科夫决策过程MDP【David Silver强化学习公开课之二】马尔可夫决策过程MDPreinforcement learning,增强学习:Markov Decision ProcessesDQN(Deep Q-learning)从入门到放弃笔记 5.Lecture 2 Markov Decision Processes PPTLecture 2 Markov Decision Processes