MULTI-ARMED BANDITS WITH DISCOUNT FACTOR NEAR ONE - THE BERNOULLI CASE

被引:18
作者
KELLY, FP
机构
关键词
D O I
10.1214/aos/1176345578
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
引用
收藏
页码:987 / 1001
页数:15
相关论文
共 17 条
[1]  
Bellman R, 1956, SANKHYA, V16, P221
[2]   BERNOULLI ONE-ARMED BANDITS - ARBITRARY DISCOUNT SEQUENCES [J].
BERRY, DA ;
FRISTEDT, B .
ANNALS OF STATISTICS, 1979, 7 (05) :1086-1105
[3]   BERNOULLI 2-ARMED BANDIT [J].
BERRY, DA .
ANNALS OF MATHEMATICAL STATISTICS, 1972, 43 (03) :871-&
[4]   DISCRETE DYNAMIC-PROGRAMMING [J].
BLACKWELL, D .
ANNALS OF MATHEMATICAL STATISTICS, 1962, 33 (02) :719-&
[5]  
Blackwell D., 1965, ANN MATH STAT, V36, P226
[6]  
Feller W., 2008, INTRO PROBABILITY TH
[7]  
GITTINS JC, 1979, J ROY STAT SOC B MET, V41, P148
[8]  
HINDERER K, 1970, F NONSTATIONARY DYNA
[9]  
KELLY FP, 1979, COMMUNICATION
[10]  
Nash P., 1973, THESIS CAMBRIDGE U