AVERAGE OPTIMAL STATIONARY POLICIES AND LINEAR-PROGRAMMING IN COUNTABLE SPACE MARKOV DECISION-PROCESSES

被引：8

作者：

LASSERRE, JB

机构：

[1] LAAS-CNRS, 31077 Toulouse Cedex

来源：

JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS | 1994年 / 183卷 / 01期

关键词：

D O I：

10.1006/jmaa.1994.1143

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

We relate average optimal stationary policies in countable space Markov decision processes and optimal solutions of an associated infinite dimensional linear program. Using the theory of linear programming in abstract spaces, sufficient conditions for existence of optimal solutions are presented and some previous ones are interpreted. (C) 1994 Academic Press, Inc.

引用

页码：233 / 249

页数：17

共 50 条

[41] DISCOUNTED AND AVERAGE MARKOV DECISION-PROCESSES WITH UNBOUNDED REWARDS - NEW CONDITIONS
QI, YH
[J]. JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 1992, 171 (01) : 111 - 124
[42] MARKOV DECISION-PROCESSES WITH A BOREL MEASURABLE COST FUNCTION - THE AVERAGE CASE
KURANO, M
[J]. MATHEMATICS OF OPERATIONS RESEARCH, 1986, 11 (02) : 309 - 320
[43] MARKOV DECISION-PROCESSES - DISCOUNTED EXPECTED REWARD OR AVERAGE EXPECTED REWARD
WHITE, DJ
[J]. JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 1993, 172 (02) : 375 - 384
[44] Optimal Decision Tree Policies for Markov Decision Processes
Vos, Daniel
Verwer, Sicco
[J]. PROCEEDINGS OF THE THIRTY-SECOND INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2023, 2023, : 5457 - 5465
[45] ISOTONE POLICIES FOR THE VALUE-ITERATION METHOD FOR MARKOV DECISION-PROCESSES
WHITE, DJ
[J]. OR SPEKTRUM, 1984, 6 (04) : 223 - 227
[46] WEAK CONDITIONS FOR THE EXISTENCE OF OPTIMAL STATIONARY POLICIES IN AVERAGE MARKOV DECISION CHAINS WITH UNBOUNDED COSTS
CAVAZOSCADENA, R
[J]. KYBERNETIKA, 1989, 25 (03) : 145 - 156
[47] NONEXISTENCE OF EPSILON-OPTIMAL RANDOMIZED STATIONARY POLICIES IN AVERAGE COST MARKOV DECISION MODELS
ROSS, SM
[J]. ANNALS OF MATHEMATICAL STATISTICS, 1971, 42 (05): : 1767 - &
[48] Approximation of average cost optimal policies for general Markov decision processes with unbounded costs
Gordienko, E
Montes-de-Oca, R
Minjarez-Sosa, A
[J]. MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 1997, 45 (02) : 245 - 263
[49] AVERAGE OPTIMAL POLICIES IN MARKOV DECISION DRIFT PROCESSES WITH APPLICATIONS TO A QUEUING AND A REPLACEMENT MODEL
HORDIJK, A
SCHOUTEN, FAV
[J]. ADVANCES IN APPLIED PROBABILITY, 1983, 15 (02) : 274 - 303
[50] Approximation of average cost optimal policies for general Markov decision processes with unbounded costs
Evgueni Gordienko
Raúl Montes-De-Oca
Adolfo Minjárez-Sosa
[J]. Mathematical Methods of Operations Research, 1997, 45 : 245 - 263

← 1 2 3 4 5 →