RE-EXAMINATION OF MARKOV POLICIES FOR ADDITIVE DECISION PROCESS - Collections

＜journal article＞
RE-EXAMINATION OF MARKOV POLICIES FOR ADDITIVE DECISION PROCESS

Creator	Creator Name Fujita, Toshiharu 藤田, 敏治 Affiliation Affiliation Name Graduate School of Mathematics, Kyushu University 九州大学大学院数理学研究科
Language	English
Publisher	Research Association of Statistical Sciences
Publisher	統計科学研究会
Date	1997-03
Source Title	Bulletin of informatics and cybernetics
Vol	29
Issue	1
First Page	51
Last Page	65
Publication Type	Version of Record
Access Rights	open access
Crossref DOI	https://doi.org/10.5109/13461
Related DOI	Bulletin of informatics and cybernetics \|\| 29(1) \|\| p51-65
Related DOI	http://bic.math.kyushu-u.ac.jp/
Related URI	Bulletin of informatics and cybernetics \|\| 29(1) \|\| p51-65
Related URI	http://bic.math.kyushu-u.ac.jp/
Relation	Bulletin of informatics and cybernetics \|\| 29(1) \|\| p51-65
Relation	http://bic.math.kyushu-u.ac.jp/
Abstract	The purpose of this paper is to ensure that Markov policy is enough for the additive decision process. We show that there exists an optimal policy which is Markov for both stochastic additive decision... process and deterministic one. We also verify through a multi-stage stochastic decision tree method that, among the class of general policies, there exist an optimal Markov policy. This fact is of course obtained by solving the regular recursive equation.show more

File	FileType	Size	Views	Description
p051	pdf	599 KB	412