ASYMPTOTICALLY EFFICIENT ADAPTIVE ALLOCATION RULES FOR THE MULTIARMED BANDIT PROBLEM WITH SWITCHING COST

被引：72
作者：
AGRAWAL, R
HEGDE, MV
TENEKETZIS, D
机构：
[1] UNIV MICHIGAN,COMMUN & SIGNAL PROC LAB,ANN ARBOR,MI 48109
[2] LOUISIANA STATE UNIV,DEPT ELECT & COMP ENGN,BATON ROUGE,LA 70803
来源：
IEEE TRANSACTIONS ON AUTOMATIC CONTROL | 1988年 / 33卷 / 10期
关键词：
Manuscript received May 14; 1987; revised March 23; 1988. Paper recommended by Associate Editor; D.A . Castanon. This work was supported by the National Science Foundation under Grant ECS-8517708. R. Agrawal and D. Teneketzis are with the Department of Electrical Engineering and Computer Science and the Communications and Signal Processing Laboratory; University of Michigan; Ann Arbor; MI 48109. M. V. Hegde is with the Department of Electrical and Computer Engineering; Louisiana State University; Baton Rouge; LA 70803. IEEE Log Number 8822541;
D O I：
10.1109/9.7243
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
8
引用
收藏
页码：899 / 905
页数：7
相关论文
共 8 条
[1]   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
[2]  
HOGAN M, 1983, 21 STANF U DEP STAT
[3]   ASYMPTOTICALLY EFFICIENT ADAPTIVE ALLOCATION RULES [J].
LAI, TL ;
ROBBINS, H .
ADVANCES IN APPLIED MATHEMATICS, 1985, 6 (01) :4-22
[4]  
LAI TL, DESIGN EXPT, P127
[5]  
LAI TL, 1984, 23RD P IEEE C DEC CO, P51
[6]  
ROBBINS H, 1952, B AM MATH SOC, V55, P527
[7]  
Ross S. M., 1983, STOCHASTIC PROCESSES
[8]  
Siegmund D., 1985, SEQUENTIAL ANAL
1