REMARKS ON THE EXISTENCE OF SOLUTIONS TO THE AVERAGE COST OPTIMALITY EQUATION IN MARKOV DECISION-PROCESSES

被引:10
作者
FERNANDEZGAUCHERAND, E [1 ]
ARAPOSTATHIS, A [1 ]
MARCUS, SI [1 ]
机构
[1] UNIV TEXAS,DEPT ELECT & COMP ENGN,AUSTIN,TX 78712
基金
美国国家科学基金会;
关键词
MARKOV DECISION PROCESSES; BOREL STATE AND ACTION SPACES; AVERAGE COST OPTIMALITY EQUATION; BOUNDED SOLUTIONS; NECESSARY CONDITIONS;
D O I
10.1016/0167-6911(90)90067-5
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Necessary conditions are given for the existence of a bounded solution to the optimality equation arising in Markov decision processes, under a long-run, expected average cost criterion. The relationships of some of our results to known sufficient conditions are also shown.
引用
收藏
页码:425 / 432
页数:8
相关论文
共 19 条
[2]  
Bertsekas D.P., 1987, ABSTRACT DYNAMIC PRO
[3]  
Bertsekas D. P., 1996, NEURO DYNAMIC PROGRA
[4]   CONTROL OF MARKOV-CHAINS WITH LONG-RUN AVERAGE COST CRITERION - THE DYNAMIC-PROGRAMMING EQUATIONS [J].
BORKAR, VS .
SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 1989, 27 (03) :642-657
[6]   NECESSARY AND SUFFICIENT CONDITIONS FOR A BOUNDED SOLUTION TO THE OPTIMALITY EQUATION IN AVERAGE REWARD MARKOV DECISION CHAINS [J].
CAVAZOSCADENA, R .
SYSTEMS & CONTROL LETTERS, 1988, 10 (01) :71-78
[7]  
FERNANDEZGAUCHE.E, 1991, THESIS U TEXAS AUSTI
[8]  
FERNANDEZGAUCHE.E, 1989, 28TH P IEEE C DEC CO, P1267
[9]  
FERNANDEZGAUCHE.E, IN PRESS ANN OPERATI
[10]  
Hernandez-Lerma O., 1989, ADAPTIVE MARKOV CONT