MARKOV DECISION PROGRAMMING-THE FIRST PASSAGE MODEL WITH DENUMERABLE STATE SPACE

作     者：LIU Jianyong LIU Ke (Institute of Applied Mathematics,Academia Sinica,Beijing 100080,China) 

出 版 物：《Systems Science and Mathematical Sciences》 (系统科学与复杂性学报(英文版))

年 卷 期：1992年第5卷第4期

页      面：340-351页

核心收录：

学科分类：0711[理学-系统科学] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 07[理学] 08[工学] 0811[工学-控制科学与工程] 081103[工学-系统工程] 

基　　金：This research was supported by the National Natural Science Foundation of China 

主　　题：Markov decision programming first passage model optimal policy 

摘      要：In this paper,we discuss MDP with discrete time parameter-the firstpassage model with denumerable state *** assumption A in this paper,we prove that an ε(0)-optimal stationary policy *** find an ε-optimalstationary policy,an algorithm of policy improvement iteration and a method ofsuccessive approximations are given.