| 非平稳MDP的期望平均准则 |
| |
| 引用本文： | 郭先平,侯振挺.非平稳MDP的期望平均准则[J].系统科学与数学,1999,19(1):123-128. |
| |
| 作者姓名： | 郭先平 侯振挺 |
| |
| 作者单位： | 中山大学数学系!广州，510275，长沙铁道学院科研所!长沙，410075 |
| |
| 基金项目： | 国家自然科学基金，广东省博士后基金 |
| |
| 摘 要： | 本文考虑的是非平稳MDP的期望平均准则，在弱遍历条件下，用概率及鞅论的方法证明了。∈（0）－最优马氏策略的存在性，作为特例，较好地解决了Feinberg和Park在1994年提及的开问题．
|
| 关 键 词： | 马氏决策过程（MDP） 期望平均准则 最优方程 最优策略 |
THE EXPECTED AVERAGE CRITERION FOR NONSTATIONARY MDP |
| |
| Xian Ping GUO,Zhen Ting HOU.THE EXPECTED AVERAGE CRITERION FOR NONSTATIONARY MDP[J].Journal of Systems Science and Mathematical Sciences,1999,19(1):123-128. |
| |
| Authors: | Xian Ping GUO Zhen Ting HOU |
| |
| Institution: | (1)The Department of Mathematics, Zhongshan University Guangzhou 510275,P.R.China;(2)Research Department .Changsha Railway University ,Changsha 410075,P.R.China |
| |
| Abstract: | In this paper, we consider the expected average criterion for nonstationary MDP. By probability and martingale method, we prove the existence of #epsilon#(>=0)-optimal Markov policies under weakly ergodic conditions. As a typical example of this paper, we solve the open problem posed by Feinberg and Park again. |
| |
| Keywords: | Markov decision processes expected average criterion optimal equation optimal policy |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《系统科学与数学》浏览原始摘要信息 |
| 点击此处可从《系统科学与数学》下载免费的PDF全文 |
