Anytime Algorithms for Multi-Armed Bandit Problems

被引：10
作者：
Kleinberg, Robert [1 ]
机构：
[1] MIT CSAIL, Cambridge, MA 02139 USA
来源：
PROCEEDINGS OF THE SEVENTHEENTH ANNUAL ACM-SIAM SYMPOSIUM ON DISCRETE ALGORITHMS | 2006年
关键词：
D O I：
10.1145/1109557.1109659
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
引用
收藏
页码：928 / 936
页数：9
相关论文
共 15 条
[1]  
Auer P, 2003, SIAM J COMPUT, V32, P48, DOI 10.1137/S0097539701398375
[2]  
Awerbuch B., 2004, Proceedings of the 36th ACM Symposiuim on Theory of Computing (STOC), P45
[3]  
AWERBUCH B, 2005, P 18 ANN C IN PRESS
[4]   Online learning in online auctions [J].
Blum, A ;
Kumar, V ;
Rudra, A ;
Wu, F .
THEORETICAL COMPUTER SCIENCE, 2004, 324 (2-3) :137-146
[5]  
Blum A, 2005, PROCEEDINGS OF THE SIXTEENTH ANNUAL ACM-SIAM SYMPOSIUM ON DISCRETE ALGORITHMS, P1156
[6]  
BODDY M, 1991, P NAT C ART INT AAAI
[7]  
COPE E, 2004, REGRET CONVERG UNPUB
[8]  
Flaxman AD, 2005, PROCEEDINGS OF THE SIXTEENTH ANNUAL ACM-SIAM SYMPOSIUM ON DISCRETE ALGORITHMS, P385
[9]   A decision-theoretic generalization of on-line learning and an application to boosting [J].
Freund, Y ;
Schapire, RE .
JOURNAL OF COMPUTER AND SYSTEM SCIENCES, 1997, 55 (01) :119-139
[10]  
Gittins John, 1974, PROGR STAT, P241266
12