| MARKOVIAN DECISION PROGRAMMING WITH RECURSIVE VECTOR-REWARD |
| |
| 作者姓名： | 刘建庸 刘克 |
| |
| 作者单位： | Institute of Applied Mathematics，Academia Sinica，Institute of Applied Mathematics，Academia Sinica |
| |
| 基金项目： | The project is supported by National Natural Science Foundation of China |
| |
| 摘 要： | In this paper, we discuss Markovian decision programming with recursive vector-reward andgive an algorithm to find optimal policies. We prove that: (1) There is a Markovian optimal policy for the nonstationary case; (2) Thereis a stationary optimal policy for the stationary case.
|
Markovian decision programming with recursive vector-reward |
| |
| Jianyong Liu,Ke Liu.MARKOVIAN DECISION PROGRAMMING WITH RECURSIVE VECTOR-REWARD[J].Acta Mathematicae Applicatae Sinica,1990,6(2):158-165. |
| |
| Authors: | Jianyong Liu Ke Liu |
| |
| Institution: | 1. Institute of Applied Mathematics, Academia Sinica, China
|
| |
| Abstract: | In this paper, we discuss Markovian decision programming with recursive vector-reward and give an algorithm to find optimal policies. We prove that: (1) There is a Markovian optimal policy for the nonstationary case; (2) There is a stationary optimal policy for the stationary case. |
| |
| Keywords: | |
| 本文献已被 CNKI SpringerLink 等数据库收录！ |
