Blackwell optimality in Markov decision processes with a Borel state space

被引：0

作者：

Yushkevich, AA

机构：

来源：

PROCEEDINGS OF THE 36TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-5 | 1997年

关键词：

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

We prove the existence of stationary Blackwell optimal policies in Markov decision processes with a Borel state space, compact action sets and bounded, continuous in action transition densities and rewards. A simultaneous Doeblin-type condition in terms of transition densities is assumed.

引用

页码：2827 / 2830

页数：4

共 50 条

[1] Blackwell optimality in the class of all policies in Markov decision chains with a Borel state space and unbounded rewards
Arie Hordijk
Alexander A. Yushkevich
[J]. Mathematical Methods of Operations Research, 1999, 50 : 421 - 448
[2] Blackwell optimality in the class of stationary policies in Markov decision chains with a Borel state space and unbounded rewards
Arie Hordijk
Alexander A. Yushkevich
[J]. Mathematical Methods of Operations Research, 1999, 49 (1) : 1 - 39
[3] Blackwell optimality in the class of all policies in Markov decision chains with a Borel state space and unbounded rewards
Hordijk, A
Yushkevich, AA
[J]. MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 1999, 50 (03) : 421 - 448
[4] Blackwell optimality in the class of stationary policies in Markov decision chains with a Borel state space and unbounded rewards
Hordijk, A
Yushkevich, AA
[J]. MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 1999, 49 (01) : 1 - 39
[5] Blackwell optimality in Markov decision processes with partial observation
Rosenberg, D
Solan, E
Vieille, N
[J]. ANNALS OF STATISTICS, 2002, 30 (04): : 1178 - 1193
[6] Deviation matrix, Laurent series and Blackwell optimality in countable state Markov decision processes
Kadota, Y
[J]. OPTIMIZATION, 2002, 51 (01) : 191 - 202
[7] RECURRENCE CONDITIONS FOR MARKOV DECISION PROCESSES WITH BOREL STATE SPACE: A SURVEY
Hernandez-Lerma, Onesimo
Montes-De-Oca, Raul
Cavazos-Cadena, Rolando
[J]. ANNALS OF OPERATIONS RESEARCH, 1991, 28 (01) : 29 - 46
[8] Blackwell optimality in Borelian continuous-in-action Markov decision processes
Yushkevich, AA
[J]. SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 1997, 35 (06) : 2157 - 2182
[9] On the Asymptotic Optimality of Finite Approximations to Markov Decision Processes with Borel Spaces
Saldi, Naci
Yuksel, Serdar
Linder, Tamas
[J]. MATHEMATICS OF OPERATIONS RESEARCH, 2017, 42 (04) : 945 - 978
[10] Constrained Markov decision processes in Borel spaces: from discounted to average optimality
Mendoza-Perez, Armando F.
Jasso-Fuentes, Hector
De-la-Cruz Courtois, Omar A.
[J]. MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 2016, 84 (03) : 489 - 525

← 1 2 3 4 5 →