AVERAGE, SENSITIVE AND BLACKWELL OPTIMAL POLICIES IN DENUMERABLE MARKOV DECISION CHAINS WITH UNBOUNDED REWARDS

被引：34

作者：

DEKKER, R ^{[1
]}

HORDIJK, A ^{[1
]}

机构：

[1] STATE UNIV LEIDEN,INST APPL MATH & COMP SCI,2312 AV LEIDEN,NETHERLANDS

来源：

关键词：

D O I：

10.1287/moor.13.3.395

中图分类号：

C93 [管理学]; O22 [运筹学];

学科分类号：

070105 ; 12 ; 1201 ; 1202 ; 120202 ;

摘要：

引用

页码：395 / 420

页数：26

共 40 条

[1] [Anonymous], 1967, GRUNDLEHREN MATH WIS, DOI DOI 10.1007/978-3-642-49686-8
[2] Bather J., 1973, Advances in Applied Probability, V5, P328, DOI 10.2307/1426039
[3] Bather JA, 1973, ADV APPL PROBAB, V5, P541
[4] DISCRETE DYNAMIC-PROGRAMMING
BLACKWELL, D
[J]. ANNALS OF MATHEMATICAL STATISTICS, 1962, 33 (02): : 719 - &
[5] BLACKWELL D, 1967, 5TH P BERK S MATH ST, V1, P415
[6] Blackwell D., 1965, ANN MATH STAT, V36, P226
[7] Dekker R., 1985, THESIS U LEIDEN
[8] CONTRACTION MAPPINGS IN THEORY UNDERLYING DYNAMIC PROGRAMMING
DENARDO, EV
[J]. SIAM REVIEW, 1967, 9 (02) : 165 - &
[9] AN OPTIMALITY CONDITION FOR DISCRETE DYNAMIC PROGRAMMING WITH NO DISCOUNTING
DENARDO, EV
MILLER, BL
[J]. ANNALS OF MATHEMATICAL STATISTICS, 1968, 39 (04): : 1220 - &
[10] ON THE EXISTENCE OF AVERAGE OPTIMAL POLICIES IN SEMIREGENERATIVE DECISION-MODELS
DEPPE, H
[J]. MATHEMATICS OF OPERATIONS RESEARCH, 1984, 9 (04) : 558 - 575