Successive reduction of arms in multi-armed bandits

Res. and Dev. in Intelligent Syst. XXVIII: Incorporating Applications and Innovations in Intel. Sys. XIX - AI 2011, 31st SGAI Int. Conf. on Innovative Techniques and Applications of Artificial Intel.

Volumn , Issue , 2011, Pages 181-194

  Gupta, Neha ^a   Granmo, Ole Christoffer ^b   Agrawala, Ashok ^a  

^a UNIVERSITY OF MARYLAND   (United States)

^b UNIVERSITY OF AGDER   (Norway)

Author keywords

[No Author keywords available]

Indexed keywords

ONLINE SYSTEMS; SAMPLING;

COMPUTATIONALLY EFFICIENT; CONFIDENCE THRESHOLD; MULTI ARMED BANDIT; MULTI-ARMED BANDIT PROBLEM; ONLINE ADVERTISEMENTS; ONLINE OPTIMIZATION; ORDER STATISTICS; THOMPSON SAMPLINGS;

ARTIFICIAL INTELLIGENCE;

EID: 84881535815     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1007/978-1-4471-2318-7_13     Document Type: Conference Paper

References (20)

1. D. Agarwal, B-C. Chen, and P. Elango. Explore/exploit schemes for web content optimization. In ICDM, 2009
2. R. Agrawal. Sample mean based index policies with o(log n) regret for multi-armed bandit problem. Advances in Applied Probability., 27:1054-1078, November 1995
3. P. Auer, N. Cesa-Bianchi, and P. Fischer. Finite time analysis of multi-armed bandit problem. Machine Learning, 27(2-3):235-256, 2002
4. D. Chakrabarti, R. Kumar, F. Radlinski, and E. Upfal. Mortal multi-armed bandits. In NIPS, 2008
5. O. Chapelle and L. Li. An empirical evaluation of thompson sampling. In ICML Workshop-Online Trading of Exploration and Exploitation 2, 2011
6. H. A. David. Order Statistics, volume 1 of Wiley Series in Probability and Mathematical Statistics, chapter 1, pages 1-32. John Wiley and Sons, Inc., second edition, 1981
7. J. C. Gittins. Bandit processes and dynamic allocation indices. Journal of Royal Statistical Society. Series B, 41(2):148-177, 1979
8. T. Graepel, J. Q. Candela, T. Borchert, and R. Herbrich. Web-scale bayesian click-Through rate prediction for sponsored search advertising in microsofts bing search engine. In ICML, 2010
9. O-C. Granmo. The bayesian learning automaton empirical evaluation with two-armed bernoulli bandit problems. Research and Development in Intelligent Systems XXV, pages 235-248, 2009
10. O-C. Granmo. Solving two-armed bernoulli bandit problems using a bayesian learning automaton. International Journal of Intelligent Computing and Cybernetics, 2(3):207-234, 2010
11. A. K. Gupta and S. Nadarajah. Handbook of Beta Distribution and its applications. Marcer Dekker Inc., New York, 2004
12. S. S. Gupta and S. Panchapakesan. Multiple Decision Procedures, volume 1 of Wiley Series in Probability and Mathematical Statistics, chapter 4, pages 59-93. John Wiley and Sons, Inc., second edition, 1979
13. W. Hoeffding. Probability inequalities for sums of bounded random variables. Journal of the American Statistical Association, 58(301):13-30, 1963
14. Jean-Yves, S. Bubeck, and R. Munos. Best arm identification in multi-armed bandits. In COLT, 2010
15. T. L. Lai and H. Robbins. Asymptotically efficient adaptive bandit rules. Advances in Applied Mathemetics, 1985
16. O. Maron and A. W. Moore. Hoeffding races: Accelerating model selection search for classification and function approximation. In NIPS, 1994
17. B. C. May, N. Korda, A. Lee, and D. S. Leslie. Optimistic bayesian sampling in contextualbandit problems. Submitted to the Annals of Applied Probability
18. T. Norheim, T. Brdland, O-C. Granmo, and B. J. Oommen. A generic solution to multiarmed bernoulli bandit problems based on random sampling from sibling conjugate priors. In ICAART, 2010
19. W. R. Thompson. On the likelihood that one unknown probability exceeds another in view of the evidence of two samples. Biometrika, 1933
20. J. Wyatt. Exploration and inference in learning from reinforcement. Ph.D. thesis, University of Edinburgh, 1997