Semi-infinite Markov decision processes
文献类型：期刊论文
| 作者 | Chen, M; Filar, JA; Liu, K
|
| 刊名 | MATHEMATICAL METHODS OF OPERATIONS RESEARCH
 |
| 出版日期 | 2000-02-01 |
| 卷号 | 51期号:1页码:115-137 |
| 关键词 | semi-infinite Markov decision processes optimal strategy epsilon-optimal |
| ISSN号 | 1432-2994 |
| 英文摘要 | In this paper discounted and average Markov decision processes with finite state space and countable action set (semi-infinite MDP for short) are discussed. Without ordinary continuity and compactness conditions, for discounted semi-infinite MDP we have shown that by exploiting the results on semi-infinite linear programming due to Tijs [20] our semi-infinite discounted MDP can be approximated by a sequence of finite discounted MDPs and even in a semi-infinite discounted MDP it is sufficient to restrict ourselves to the class of deterministic stationary strategies. For average reward case we still prove that under some conditions the supremum in the class of general strategies is equivalent to the supremum in the class of deterministic stationary strategies. A counterexample shows that these conditions can not be easily relaxed. |
| WOS研究方向 | Operations Research & Management Science ; Mathematics |
| 语种 | 英语 |
| WOS记录号 | WOS:000087215000006 |
| 出版者 | PHYSICA VERLAG GMBH |
| 源URL | [http://ir.amss.ac.cn/handle/2S8OKBNM/15670]  |
| 专题 | 应用数学研究所 |
| 通讯作者 | Chen, M |
| 作者单位 | 1.Univ Maryland Baltimore Cty, Dept Math & Stat, Baltimore, MD 21250 USA 2.Univ S Australia, Sch Math, The Levels, SA 5095, Australia 3.Acad Sinica, Inst Appl Math, Beijing 100080, Peoples R China |
| 推荐引用方式 GB/T 7714 | Chen, M,Filar, JA,Liu, K. Semi-infinite Markov decision processes[J]. MATHEMATICAL METHODS OF OPERATIONS RESEARCH,2000,51(1):115-137. |
| APA | Chen, M,Filar, JA,&Liu, K.(2000).Semi-infinite Markov decision processes.MATHEMATICAL METHODS OF OPERATIONS RESEARCH,51(1),115-137. |
| MLA | Chen, M,et al."Semi-infinite Markov decision processes".MATHEMATICAL METHODS OF OPERATIONS RESEARCH 51.1(2000):115-137. |
入库方式： OAI收割
来源：数学与系统科学研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。