【RLchina第二讲】 Foundations of Reinforcement Learning
文章目录策略方法VIPIVIandPI:收敛性分析Qlearningn-steptransitionprobability:anexampleComputationallearningtheoryProbablyApproximatelyCorrect(PAC)learning理论分析**LearningboundforfiniteH-consistentcase**:**Learningboun