Notes on average Markov decision processes with a minimum-variance criterion

CSpace

	Notes on average Markov decision processes with a minimum-variance criterion
	Liu, JY
	2002-04-01
发表期刊	OPERATIONS RESEARCH LETTERS
ISSN	0167-6377
卷号	30 期号:2 页码:107-116
摘要	In this paper we consider the optimization problem of the variance of the reward for the nonstationary average Markov decision processes (MDP, for short). Examples in this paper show that there are mistakes in proofs of main theorems in two papers, Kurano [(J. Math, Anal. Appl. 123 (1987) 572)] and Guo [(Math. Meth. Oper. Res. 49 (1999) 87-96)] which investigated the optimization problems of the variance of the sun of costs for the average MDP. We propose a variance criterion which is different from that investigated by Kurano (1987) and Guo (1999) and we prove that there exists a Markov policy which is epsilon-strong variance optimal policy for any epsilon > 0 under some appropriate conditions. (C) 2002 Elsevier Science B.V. All tights reserved.
关键词	Markov decision processes nonstationary MDP average criterion variance criterion strong variance optimal policy
语种	英语
WOS研究方向	Operations Research & Management Science
WOS类目	Operations Research & Management Science
WOS记录号	WOS:000176621900007
出版者	ELSEVIER SCIENCE BV
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/17415
专题	中国科学院数学与系统科学研究院
通讯作者	Liu, JY
作者单位	Acad Sinica, Inst Appl Math, Beijing 100080, Peoples R China
推荐引用方式 GB/T 7714	Liu, JY. Notes on average Markov decision processes with a minimum-variance criterion[J]. OPERATIONS RESEARCH LETTERS,2002,30(2):107-116.
APA	Liu, JY.(2002).Notes on average Markov decision processes with a minimum-variance criterion.OPERATIONS RESEARCH LETTERS,30(2),107-116.
MLA	Liu, JY."Notes on average Markov decision processes with a minimum-variance criterion".OPERATIONS RESEARCH LETTERS 30.2(2002):107-116.