A UNIFIED APPROACH TO ADAPTIVE-CONTROL OF AVERAGE REWARD MARKOV DECISION-PROCESSES

被引：2

作者：

HUBNER, G ^{[1
]}

机构：

[1] UNIV HAMBURG,INST MATH STOCHASTIK,D-2000 HAMBURG 13,FED REP GER

来源：

OR SPEKTRUM | 1988年 / 10卷 / 03期

关键词：

D O I：

10.1007/BF01740510

中图分类号：

C93 [管理学]; O22 [运筹学];

学科分类号：

070105 ; 12 ; 1201 ; 1202 ; 120202 ;

摘要：

引用

收藏

页码：161 / 166

页数：6

相关论文

共 16 条

[1] Acosta-Abreu R. S., 1985, Control and Cybernetics, V14, P313
[2] BARANOV VV, 1981, CYBERNETICS+, V17, P815
[3] CONTRACTION MAPPINGS UNDERLYING UNDISCOUNTED MARKOV DECISION PROBLEMS
FEDERGRUEN, A
SCHWEITZER, PJ
TIJMS, HC
[J]. JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 1978, 65 (03) : 711 - 730
[4] NONSTATIONARY MARKOV DECISION-PROBLEMS WITH CONVERGING PARAMETERS
FEDERGRUEN, A
SCHWEITZER, PJ
[J]. JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 1981, 34 (02) : 207 - 241
[5] OPTIMALITY EQUATION IN AVERAGE COST DENUMERABLE STATE SEMI-MARKOV DECISION PROBLEMS, RECURRENCY CONDITIONS AND ALGORITHMS
FEDERGRUEN, A
TIJMS, HC
[J]. JOURNAL OF APPLIED PROBABILITY, 1978, 15 (02) : 356 - 373
[6] ADAPTIVE-CONTROL OF DISCOUNTED MARKOV DECISION CHAINS
HERNANDEZLERMA, O
MARCUS, SI
[J]. JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 1985, 46 (02) : 227 - 235
[7] HINDERER K, 1970, F NONSTATIONARY DYNA
[8] BOUNDS AND GOOD POLICIES IN STATIONARY FINITE-STAGE MARKOVIAN DECISION-PROBLEMS
HUBNER, G
[J]. ADVANCES IN APPLIED PROBABILITY, 1980, 12 (01) : 154 - 173
[9] HUBNER G, 1977, DYNAMISCHE OPTIMIERU, V98, P57
[10] LEARNING ALGORITHMS FOR MARKOV DECISION-PROCESSES
KURANO, M
[J]. JOURNAL OF APPLIED PROBABILITY, 1987, 24 (01) : 270 - 276