BOUNDS ON GAIN OF A MARKOV DECISION PROCESS

被引：16

作者：

HASTINGS, NA

机构：

来源：

关键词：

D O I：

10.1287/opre.19.1.240

中图分类号：

C93 [管理学];

学科分类号：

12 ; 1201 ; 1202 ; 120202 ;

摘要：

引用

页码：240 / &

共 7 条

[1] A MARKOVIAN DECISION PROCESS [J].

BELLMAN, R .

JOURNAL OF MATHEMATICS AND MECHANICS, 1957, 6 (05) :679-684

[2] OPTIMIZATION OF DISCOUNTED MARKOV DECISION PROBLEMS [J].

HASTINGS, NA .

[3] SOME NOTES ON DYNAMIC PROGRAMMING AND REPLACEMENT [J].

HASTINGS, NA .

[4]

Howard RonaldA., 1960, DYNAMIC PROGRAMMING

[5] MARKOV-RENEWAL PROGRAMMING .1. FORMULATION, FINITE RETURN MODELS [J].

JEWELL, WS .

[6] ON FINDING MAXIMAL GAIN FOR MARKOV DECISION PROCESSES [J].

ODONI, AR .

[7]

White D. J., 1963, J MATH ANAL APPL, V6, P373