Finite horizon semi-Markov decision processes with multiple constraints

被引：0

作者：

Huang, Yonghui ^{[1
]}

机构：

[1] Sun Yat Sen Univ, Sch Math & Computat Sci, Guangzhou 510275, Guangdong, Peoples R China

来源：

2014 11TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA) | 2014年

关键词：

Semi-Markov decision processes; expected finite horizon reward; occupancy measure; constrained-optimal policy; linear programm; TOTAL-COST CRITERIA; POLICIES;

D O I：

暂无

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 focuses on solving a finite horizon semi-Markov decision process with multiple constraints. We convert the problem to a constrained absorbing discrete-time Markov decision process and then to an equivalent linear programm over a class of occupancy measures. The existence, characterization and computation of constrained-optimal policies are established under suitable conditions. An example is given to demonstrate our results.

引用

页码：1761 / 1768

页数：8

共 21 条

[1] Constrained Markov decision processes with total cost criteria: Lagrangian approach and dual linear program [J].

Altman, E .

MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 1998, 48 (03) :387-417

[2]

ALTMAN E, 1996, MATH METHOD OPER RES, V43, P45

[3]

[Anonymous], 1996, Stochastic Processes

[4]

Bertsekas D., 1996, Stochastic optimal control: the discrete-time case, V5

[5] TIME-AVERAGE OPTIMAL CONSTRAINED SEMI-MARKOV DECISION-PROCESSES [J].

BEUTLER, FJ ;

ROSS, KW .

ADVANCES IN APPLIED PROBABILITY, 1986, 18 (02) :341-359

[6] Non-randomized policies for constrained Markov decision processes [J].

Chen, Richard C. ;

Feinberg, Eugene A. .

MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 2007, 66 (01) :165-179

[7]

Feinberg E. A., 1994, ZOR, Methods and Models of Operations Research, V39, P257, DOI 10.1007/BF01435458

[8] Continuous time discounted jump Markov decision processes: A discrete-event approach [J].

Feinberg, EA .

MATHEMATICS OF OPERATIONS RESEARCH, 2004, 29 (03) :492-524

[9] Splitting Randomized Stationary Policies in Total-Reward Markov Decision Processes [J].

Feinberg, Eugene A. ;

Rothblum, Uriel G. .

MATHEMATICS OF OPERATIONS RESEARCH, 2012, 37 (01) :129-153

[10] Optimal policies for constrained average-cost Markov decision processes [J].

Gonzalez-Hernandez, Juan ;

Villarreal, Cesar E. .

TOP, 2011, 19 (01) :107-120

← 1 2 3 →