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

[41] Strong average optimality for controlled nonhomogeneous Markov chains
Guo, XP
Shi, P
Zhu, WP
[J]. STOCHASTIC ANALYSIS AND APPLICATIONS, 2001, 19 (01) : 115 - 134
[42] Fuzzy decision processes with an average reward criterion
Kurano, M
Yasuda, M
Nakagami, JI
Yoshida, Y
[J]. MATHEMATICAL AND COMPUTER MODELLING, 1999, 30 (7-8) : 7 - 20
[43] A note on optimality conditions for continuous-time Markov decision processes with average cost criterion
Guo, XP
Liu, K
[J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2001, 46 (12) : 1984 - 1989
[44] SECOND ORDER OPTIMALITY IN MARKOV DECISION CHAINS
Sladky, Karel
[J]. KYBERNETIKA, 2017, 53 (06) : 1086 - 1099
[45] Mean Variance Optimality in Markov Decision Chains
Sladky, Karel
Sitar, Milan
[J]. PROCEEDINGS OF THE 23RD INTERNATIONAL CONFERENCE ON MATHEMATICAL METHODS IN ECONOMICS 2005, 2005, : 350 - 357
[46] GROWTH OPTIMALITY FOR BRANCHING MARKOV DECISION CHAINS
ROTHBLUM, UG
WHITTLE, P
[J]. MATHEMATICS OF OPERATIONS RESEARCH, 1982, 7 (04) : 582 - 601
[47] Sample path optimality for a Markov optimization problem
Hunt, FY
[J]. STOCHASTIC PROCESSES AND THEIR APPLICATIONS, 2005, 115 (05) : 769 - 779
[48] REWARD REVISION AND THE AVERAGE REWARD MARKOV DECISION-PROCESS
WHITE, CC
SCHERER, WT
[J]. OR SPEKTRUM, 1987, 9 (04) : 203 - 211
[49] Transient and Average Markov Reward Chains with Applications to Finance
Sladky, Karel
[J]. 34TH INTERNATIONAL CONFERENCE MATHEMATICAL METHODS IN ECONOMICS (MME 2016), 2016, : 773 - 778
[50] Optimality equations and inequalities in a class of risk-sensitive average cost Markov decision chains
Rolando Cavazos-Cadena
[J]. Mathematical Methods of Operations Research, 2010, 71 : 47 - 84

← 1 2 3 4 5 →