Sample-path optimality and variance-minimization of average cost Markov control processes

被引：47

作者：

Hernández-Lerma, O

Vega-Amaya, O

Carrasco, G

机构：

[1] Inst Politecn Nacl, Ctr Invest & Estudios Avanzados, Dept Matemat, Mexico City 07000, DF, Mexico

[2] Sonoma State Univ, Dept Matemat, Hermosillo, Sonora, Mexico

[3] Univ Nacl Autonoma Mexico, Fac Ciencia, Dept Matemat, Mexico City 04510, DF, Mexico

来源：

SIAM JOURNAL ON CONTROL AND OPTIMIZATION | 1999年 / 38卷 / 01期

关键词：

(discrete-time) Markov control processes; average cost criteria; sample-path average cost; expected average cost; canonical policies; average variance;

D O I：

10.1137/S0363012998340673

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper studies several average-cost criteria for Markov control processes on Borel spaces with possibly unbounded costs. Under suitable hypotheses we show (i) the existence of a sample-path average cost (SPAC-) optimal stationary policy; (ii) a stationary policy is SPAC-optimal if and only if it is expected average cost (EAC-) optimal; and (iii) within the class of stationary SPAC-optimal (equivalently, EAC-optimal) policies there exists one with a minimal limiting average variance.

引用

页码：79 / 93

页数：15

共 50 条

[41] A note on optimality conditions for continuous-time Markov decision processes with average cost criterion
Guo, XP
Liu, K
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2001, 46 (12) : 1984 - 1989
[42] AVERAGE COST OPTIMALITY INEQUALITY FOR MARKOV DECISION PROCESSES WITH BOREL SPACES AND UNIVERSALLY MEASURABLE POLICIES
Yu, Huizhen
SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 2020, 58 (04) : 2469 - 2502
[43] Average optimality for adaptive Markov control processes with unbounded costs and unknown disturbance distribution
Minjárez-Sosa, JA
MARKOV PROCESSES AND CONTROLLED MARKOV CHAINS, 2002, : 111 - 134
[44] Sample-Path Based Performance Sensitivity Construction of Semi-Markov Systems
Li, Yanjie
Zhang, Junyu
PROCEEDINGS OF THE 35TH CHINESE CONTROL CONFERENCE 2016, 2016, : 2449 - 2453
[45] Value iteration in average cost Markov control processes on borel spaces
MontesdeOca, R
HernandezLerma, O
ACTA APPLICANDAE MATHEMATICAE, 1996, 42 (02) : 203 - 222
[46] Average cost Markov control processes: stability with respect to the Kantorovich metric
Gordienko, Evgueni
Lemus-Rodriguez, Enrique
Montes-de-Oca, Raul
MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 2009, 70 (01) : 13 - 33
[47] Average cost Markov control processes: stability with respect to the Kantorovich metric
Evgueni Gordienko
Enrique Lemus-Rodríguez
Raúl Montes-de-Oca
Mathematical Methods of Operations Research, 2009, 70 : 13 - 33
[48] Policy iteration for average cost Markov control processes on Borel spaces
HernandezLerma, O
Lasserre, JB
ACTA APPLICANDAE MATHEMATICAE, 1997, 47 (02) : 125 - 154
[49] Policy Iteration for Average Cost Markov Control Processes on Borel Spaces
Onésimo Hernández-Lerma
Jean B. Lasserre
Acta Applicandae Mathematica, 1997, 47 : 125 - 154
[50] Risk-Sensitive and Average Optimality in Markov Decision Processes
Sladky, Karel
PROCEEDINGS OF 30TH INTERNATIONAL CONFERENCE MATHEMATICAL METHODS IN ECONOMICS, PTS I AND II, 2012, : 799 - 804

← 1 2 3 4 5 →