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

[21] Finite-State Approximations to Constrained Markov Decision Processes with Borel Spaces
Saldi, Naci
Yuksel, Serdar
Linder, Tamas
[J]. 2015 53RD ANNUAL ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING (ALLERTON), 2015, : 567 - 572
[22] Estimation of the stationary distribution of semi-Markov processes with Borel state space
Limnios, N.
[J]. STATISTICS & PROBABILITY LETTERS, 2006, 76 (14) : 1536 - 1542
[23] Approximation of Markov decision processes with general state space
Dufour, F.
Prieto-Rumeau, T.
[J]. JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 2012, 388 (02) : 1254 - 1267
[24] THE AVERAGE COST OPTIMALITY EQUATION FOR MARKOV CONTROL PROCESSES ON BOREL SPACES
MONTESDEOCA, R
[J]. SYSTEMS & CONTROL LETTERS, 1994, 22 (05) : 351 - 357
[25] MARKOV DECISION PROCESSES WITH A NEW OPTIMALITY CRITERION
JAQUETTE, SC
[J]. ANNALS OF MATHEMATICAL STATISTICS, 1971, 42 (05): : 1793 - &
[26] Finite-State Approximation of Markov Decision Processes with Unbounded Costs and Borel Spaces
Saldi, Naci
Yuksel, Serdar
Linder, Tumas
[J]. 2015 54TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2015, : 5085 - 5090
[27] Nonstationary Policies and Average Optimality in Multichain Markov Decision Processes with a General Action Space
A. Y. Golubin
[J]. Journal of Mathematical Sciences, 2004, 123 (1) : 3733 - 3740
[28] Semiparametric estimation of Markov decision processes with continuous state space
Srisuma, Sorawoot
Linton, Oliver
[J]. JOURNAL OF ECONOMETRICS, 2012, 166 (02) : 320 - 341
[29] Solution to the risk-sensitive average cost optimality equation in a class of Markov decision processes with finite state space
Cavazos-Cadena, R
[J]. MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 2003, 57 (02) : 263 - 285
[30] Solution to the risk-sensitive average cost optimality equation in a class of Markov decision processes with finite state space
Rolando Cavazos-Cadena
[J]. Mathematical Methods of Operations Research, 2003, 57 : 263 - 285

← 1 2 3 4 5 →