LEARNING CONTROL OF FINITE MARKOV-CHAINS WITH AN EXPLICIT TRADE-OFF BETWEEN ESTIMATION AND CONTROL

被引：21

作者：

SATO, M ^{[1
]}

ABE, K ^{[1
]}

TAKEDA, H ^{[1
]}

机构：

[1] TOYOHASHI UNIV TECHNOL,DEPT INFORMAT & COMP SCI,TOYOHASHI,AICHI 440,JAPAN

来源：

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS | 1988年 / 18卷 / 05期

关键词：

D O I：

10.1109/21.21595

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

引用

页码：677 / 684

页数：8

共 16 条

[1] TECHNIQUE FOR DUAL ADAPTIVE-CONTROL [J].

ALSTER, J ;

BELANGER, PR .

AUTOMATICA, 1974, 10 (06) :627-634

[2]

BECKER A, 1981, 811 U MAR MATH RES R

[3] ADAPTIVE-CONTROL OF MARKOV-CHAINS - FINITE PARAMETER SET [J].

BORKAR, V ;

VARAIYA, P .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1979, 24 (06) :953-957

[4] STRONG CONSISTENCY OF A MODIFIED MAXIMUM-LIKELIHOOD ESTIMATOR FOR CONTROLLED MARKOV-CHAINS [J].

DOSHI, B ;

SHREVE, SE .

JOURNAL OF APPLIED PROBABILITY, 1980, 17 (03) :726-734

[5] RECURSIVE ALGORITHMS FOR ADAPTIVE-CONTROL OF FINITE MARKOV-CHAINS [J].

ELFATTAH, YM .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1981, 11 (02) :135-144

[6]

HOWARD RA, 1971, PYNAMIC PROBABILISTI, V2

[7] A NEW FAMILY OF OPTIMAL ADAPTIVE CONTROLLERS FOR MARKOV-CHAINS [J].

KUMAR, PR ;

BECKER, A .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1982, 27 (01) :137-146

[8] OPTIMAL ADAPTIVE CONTROLLERS FOR UNKNOWN MARKOV-CHAINS [J].

KUMAR, PR ;

LIN, W .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1982, 27 (04) :765-774

[9]

Mandl P., 1974, Advances in Applied Probability, V6, P40, DOI 10.2307/1426206

[10]

Martin James John, 1967, BAYESIAN DECISION PR

← 1 2 →