ASYMPTOTICALLY EFFICIENT ADAPTIVE ALLOCATION SCHEMES FOR CONTROLLED IID PROCESSES - FINITE PARAMETER SPACE

被引：38

作者：

AGRAWAL, R

TENEKETZIS, D

ANANTHARAM, V

机构：

[1] UNIV MICHIGAN,DEPT ELECT & COMP ENGN,ANN ARBOR,MI 48109

[2] CORNELL UNIV,SCH ELECT ENGN,ITHACA,NY 14853

来源：

IEEE TRANSACTIONS ON AUTOMATIC CONTROL | 1989年 / 34卷 / 03期

关键词：

D O I：

10.1109/9.16415

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

引用

页码：258 / 267

页数：10

共 9 条

[1] ASYMPTOTICALLY EFFICIENT ADAPTIVE ALLOCATION RULES FOR THE MULTIARMED BANDIT PROBLEM WITH SWITCHING COST [J].

AGRAWAL, R ;

HEGDE, MV ;

TENEKETZIS, D .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1988, 33 (10) :899-905

[2] ASYMPTOTICALLY EFFICIENT ALLOCATION RULES FOR THE MULTIARMED BANDIT PROBLEM WITH MULTIPLE PLAYS .1. IID REWARDS [J].

ANANTHARAM, V ;

VARAIYA, P ;

WALRAND, J .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1987, 32 (11) :968-976

[3]

BATHER JA, 1983, SPRINGER VERLAG LECT, V20, P1

[4]

Ellis R. S., 1985, ENTROPY LARGE DEVIAT

[5]

Kumar P. R., 1986, STOCHASTIC SYSTEMS E

[6] ASYMPTOTICALLY EFFICIENT ADAPTIVE ALLOCATION RULES [J].

LAI, TL ;

ROBBINS, H .

ADVANCES IN APPLIED MATHEMATICS, 1985, 6 (01) :4-22

[7]

LAI TL, DESIGN EXPT

[8]

Ross S. M., 1983, STOCHASTIC PROCESSES

[9] AN ASYMPTOTIC MINIMAX THEOREM FOR THE 2 ARMED BANDIT PROBLEM [J].

VOGEL, W .

ANNALS OF MATHEMATICAL STATISTICS, 1960, 31 (02) :444-451

← 1 →