NECESSARY AND SUFFICIENT CONDITIONS FOR A BOUNDED SOLUTION TO THE OPTIMALITY EQUATION IN AVERAGE REWARD MARKOV DECISION CHAINS
被引:16
作者:
CAVAZOSCADENA, R
论文数: 0引用数: 0
h-index: 0
机构:
UNIV AUTONOMA AGR ANTONIO NARRO,DEPT ESTADIST & CALCULO,SALTILLO,COAHUILA,MEXICOUNIV AUTONOMA AGR ANTONIO NARRO,DEPT ESTADIST & CALCULO,SALTILLO,COAHUILA,MEXICO
CAVAZOSCADENA, R
[1
]
机构:
[1] UNIV AUTONOMA AGR ANTONIO NARRO,DEPT ESTADIST & CALCULO,SALTILLO,COAHUILA,MEXICO
MATHEMATICAL TECHNIQUES - State Space Methods - OPTIMIZATION;
D O I:
10.1016/0167-6911(88)90043-6
中图分类号:
TP [自动化技术、计算机技术];
学科分类号:
0812 ;
摘要:
We consider average reward Markov decision processes with discrete time parameter and denumerable state space. We are concerned with the following problem: find necessary and sufficient conditions so that, for arbitrary bounded reward function, the corresponding average reward optimality equation has a bounded solution. This problem is solved for a class of systems including the case in which, under the action of any stationary policy, the state space is an irreducible positive recurrent class.