Approximation of average cost optimal policies for general Markov decision processes with unbounded costs

被引：0

作者：

Evgueni Gordienko

Raúl Montes-De-Oca

Adolfo Minjárez-Sosa

机构：

[1] Universidad Autónoma Metropolitana — Iztapalapa,Departamento de Matemáticas

[2] Universidad de Sonora,Departamento de Matemáticas

来源：

Mathematical Methods of Operations Research | 1997年 / 45卷

关键词：

Markov Decision Process; Average Cost Criterion; Value Iteration; Approximation of Optimal Policy; Geometrical Convergence;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

The aim of the paper is to show that Lyapunov-like ergodicity conditions on Markov decision processes with Borel state space and possibly unbounded cost provide the approximation of an average cost optimal policy by solvingn-stage optimization problems (n = 1, 2, ...). The used approach ensures the exponential rate of convergence. The approximation of this type would be useful to find adaptive procedures of control and to estimate stability of an optimal control under disturbances of the transition probability.

引用

页码：245 / 263

页数：18

共 50 条

[1] Approximation of average cost optimal policies for general Markov decision processes with unbounded costs
Gordienko, E
Montes-de-Oca, R
Minjarez-Sosa, A
MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 1997, 45 (02) : 245 - 263
[2] Algorithm to identify and compute average optimal policies in multichain Markov decision processes
Leizarowitz, A
MATHEMATICS OF OPERATIONS RESEARCH, 2003, 28 (03) : 553 - 586
[3] Value Iteration and Action ε-Approximation of Optimal Policies in Discounted Markov Decision Processes
Montes-De-Oca, Raul
Lemus-Rodriguez, Enrique
RECENT ADVANCES IN APPLIED MATHEMATICS, 2009, : 213 - +
[4] A note on the existence of optimal stationary policies for average Markov decision processes with countable states
Xia, Li
Guo, Xianping
Cao, Xi-Ren
AUTOMATICA, 2023, 151
[5] Nonstationary Policies and Average Optimality in Multichain Markov Decision Processes with a General Action Space
A. Y. Golubin
Journal of Mathematical Sciences, 2004, 123 (1) : 3733 - 3740
[6] Adaptive control for discrete-time Markov processes with unbounded costs: Average criterion
Evgueni I. Gordienko
J. Adolfo Minjárez-Sosa
Mathematical Methods of Operations Research, 1998, 48 : 37 - 55
[7] Adaptive control for discrete-time Markov processes with unbounded costs: Average criterion
Gordienko, EI
Minjarez-Sosa, JA
MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 1998, 48 (01) : 37 - 55
[8] A PERTURBATION APPROACH TO APPROXIMATE VALUE ITERATION FOR AVERAGE COST MARKOV DECISION PROCESSES WITH BOREL SPACES AND BOUNDED COSTS
Vega-Amaya, Oscar
Lopez-Borbon, Joaqun
KYBERNETIKA, 2019, 55 (01) : 81 - 113
[9] Average Cost Markov Decision Processes with Weakly Continuous Transition Probabilities
Feinberg, Eugene A.
Kasyanov, Pavlo O.
Zadoianchuk, Nina V.
MATHEMATICS OF OPERATIONS RESEARCH, 2012, 37 (04) : 591 - 607
[10] LINEAR-PROGRAMMING AND AVERAGE OPTIMALITY OF MARKOV CONTROL PROCESSES ON BOREL SPACES - UNBOUNDED COSTS
HERNANDEZLERMA, O
LASSERRE, JB
SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 1994, 32 (02) : 480 - 500

← 1 2 3 4 5 →