Semi-infinite Markov decision processes

CSpace > 应用数学研究所

	Semi-infinite Markov decision processes
	Chen, M ; Filar, JA ; Liu, K
	2000-02-01
发表期刊	MATHEMATICAL METHODS OF OPERATIONS RESEARCH
ISSN	1432-2994
卷号	51 期号:1 页码:115-137
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.
关键词	semi-infinite Markov decision processes optimal strategy epsilon-optimal
语种	英语
WOS研究方向	Operations Research & Management Science ; Mathematics
WOS类目	Operations Research & Management Science ; Mathematics, Applied
WOS记录号	WOS:000087215000006
出版者	PHYSICA VERLAG GMBH
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/15671
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.