WEAK CONDITIONS FOR AVERAGE OPTIMALITY IN MARKOV CONTROL PROCESSES

被引：8

作者：

HERNANDEZLERMA, O

LASSERRE, JB

机构：

[1] INST POLITECN NACL,CINVESTAV,DEPT MATH,MEXICO CITY 07000,DF,MEXICO

[2] CNRS,LAAS,F-31077 TOULOUSE,FRANCE

来源：

SYSTEMS & CONTROL LETTERS | 1994年 / 22卷 / 04期

关键词：

(DISCRETE-TIME) MARKOV CONTROL PROCESSES; AVERAGE COST CRITERION;

D O I：

10.1016/0167-6911(94)90060-4

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper we study the existence of average cost optimal policies for Markov control processes on Borel spaces and with possibly unbounded costs and controls. Under assumptions weaker than those used in the previous literature, we show that the 'optimality inequality' holds everywhere, and that there exists a stationary policy which is optimal whenever the initial state lies in a possibly proper subset of the state space. This is in contrast to previous works where an implicit 'unichain' assumption ensures optimality for all initial states.

引用

页码：287 / 291

页数：5

共 50 条

[21] Average Optimality in Nonhomogeneous Infinite Horizon Markov Decision Processes
Wachs, Allise O.
Schochetman, Irwin E.
Smith, Robert L.
MATHEMATICS OF OPERATIONS RESEARCH, 2011, 36 (01) : 147 - 164
[22] RISK-SENSITIVE AVERAGE OPTIMALITY IN MARKOV DECISION PROCESSES
Sladky, Karel
KYBERNETIKA, 2018, 54 (06) : 1218 - 1230
[23] Markov Control with Rare State Observation: Average Optimality
Winkelmann, S.
MARKOV PROCESSES AND RELATED FIELDS, 2017, 23 (01) : 1 - 34
[24] NECESSARY CONDITIONS FOR OPTIMALITY IN THE CONTROL OF PIECEWISE-DETERMINISTIC MARKOV-PROCESSES
DAVIS, MHA
PROCEEDINGS OF THE 28TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-3, 1989, : 719 - 723
[25] Average optimality in Markov control processes via discounted-cost problems and linear programming
HernandezLerma, O
Lasserre, JB
SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 1996, 34 (01) : 295 - 310
[26] Sample-path optimality and variance-minimization of average cost Markov control processes
Hernández-Lerma, Onésimo
Vega-Amaya, Oscar
Carrasco, Guadalupe
SIAM Journal on Control and Optimization, 38 (01): : 79 - 93
[27] Sample-path optimality and variance-minimization of average cost Markov control processes
Hernández-Lerma, O
Vega-Amaya, O
Carrasco, G
SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 1999, 38 (01) : 79 - 93
[28] 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
[29] Risk-Sensitivity and Average Optimality in Markov and Semi-Markov Reward Processes
Sladky, Karel
38TH INTERNATIONAL CONFERENCE ON MATHEMATICAL METHODS IN ECONOMICS (MME 2020), 2020, : 537 - 543
[30] ON STRONG AVERAGE OPTIMALITY OF MARKOV DECISION-PROCESSES WITH UNBOUNDED COSTS
GHOSH, MK
MARCUS, SI
OPERATIONS RESEARCH LETTERS, 1992, 11 (02) : 99 - 104

← 1 2 3 4 5 →