A Counterexample on Sample-Path Optimality in Stable Markov Decision Chains with the Average Reward Criterion

被引：0

作者：

Rolando Cavazos-Cadena

Raúl Montes-de-Oca

Karel Sladký

机构：

[1] Universidad Autónoma Agraria Antonio Narro,Departamento de Estadística y Cálculo

[2] Universidad Autónoma Metropolitana,Departamento de Matemáticas

[3] Institute of Information Theory and Automation,undefined

来源：

Journal of Optimization Theory and Applications | 2014年 / 163卷

关键词：

Strong sample-path optimality; Lyapunov function condition; Stationary policy; Expected average reward criterion;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

This note deals with Markov decision chains evolving on a denumerable state space. Under standard continuity-compactness requirements, an explicit example is provided to show that, with respect to a strong sample-path average reward criterion, the Lyapunov function condition does not ensure the existence of an optimal stationary policy.

引用

页码：674 / 684

页数：10

共 50 条

[1] A Counterexample on Sample-Path Optimality in Stable Markov Decision Chains with the Average Reward Criterion
Cavazos-Cadena, Rolando
Montes-de-Oca, Raul
Sladky, Karel
[J]. JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 2014, 163 (02) : 674 - 684
[2] SAMPLE-PATH OPTIMAL STATIONARY POLICIES IN STABLE MARKOV DECISION CHAINS WITH THE AVERAGE REWARD CRITERION
Cavazos-Cadena, Rolando
Montes-De-Oca, Raul
Sladky, Karel
[J]. JOURNAL OF APPLIED PROBABILITY, 2015, 52 (02) : 419 - 440
[3] Denumerable controlled markov chains with average reward criterion. Sample path optimality
Cavazos-Cadena, Rolando
Fernandez-Gaucherand, Emmanuel
[J]. ZOR. Zeitschrift Fuer Operations Research, 41 (01):
[4] A COUNTEREXAMPLE ON THE OPTIMALITY EQUATION IN MARKOV DECISION CHAINS WITH THE AVERAGE COST CRITERION
CAVAZOSCADENA, R
[J]. SYSTEMS & CONTROL LETTERS, 1991, 16 (05) : 387 - 392
[5] Sample-path average optimality for Markov control processes
Lasserre, JB
[J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1999, 44 (10) : 1966 - 1971
[6] Average Sample-path Optimality for Continuous-time Markov Decision Processes in Polish Spaces
Quan-xin ZHU Department of Mathematics
[J]. Acta Mathematicae Applicatae Sinica, 2011, 27 (04) : 613 - 624
[7] Average sample-path optimality for continuous-time Markov decision processes in Polish spaces
Zhu, Quan-xin
[J]. ACTA MATHEMATICAE APPLICATAE SINICA-ENGLISH SERIES, 2011, 27 (04): : 613 - 624
[8] Average sample-path optimality for continuous-time Markov decision processes in Polish spaces
Quan-xin Zhu
[J]. Acta Mathematicae Applicatae Sinica, English Series, 2011, 27 : 613 - 624
[9] Sample-path optimality and variance-maximization for Markov decision processes
Q. X. Zhu
[J]. Mathematical Methods of Operations Research, 2007, 65 : 519 - 538
[10] Sample-path optimality and variance-maximization for Markov decision processes
Zhu, Q. X.
[J]. MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 2007, 65 (03) : 519 - 538

← 1 2 3 4 5 →