| MARKOV DECISION PROGRAMMING-THE FIRST PASSAGE MODEL WITH DENUMERABLE STATE SPACE |
| |
| 作者姓名： | LIU Jianyong LIU Ke |
| |
| 作者单位： | Institute of Applied Mathematics，Academia Sinica，Beijing 100080，China |
| |
| 基金项目： | This research was supported by the National Natural Science Foundation of China |
| |
| 摘 要： | In this paper,we discuss MDP with discrete time parameter-the firstpassage model with denumerable state space.Under assumption A in this paper,we prove that an ε(>0)-optimal stationary policy exists.To find an ε-optimalstationary policy,an algorithm of policy improvement iteration and a method ofsuccessive approximations are given.
|
MARKOV DECISION PROGRAMMING-THE FIRST PASSAGE MODEL WITH DENUMERABLE STATE SPACE |
| |
| LIU Jianyong LIU Ke.MARKOV DECISION PROGRAMMING-THE FIRST PASSAGE MODEL WITH DENUMERABLE STATE SPACE[J].Journal of Systems Science and Complexity,1992(4). |
| |
| Authors: | LIU Jianyong LIU Ke |
| |
| Abstract: | |
| |
| Keywords: | Markov decision programming first passage model optimal policy |
| 本文献已被 CNKI 等数据库收录！ |
