Information complexity in bandit subset selection

Journal of Machine Learning Research

Volumn 30, Issue , 2013, Pages 228-251

  Kaufmann, Emilie ^a,b   Kalyanakrishnan, Shivaram ^c  

^a INSTITUT MINES TELECOM   (France)

^b TELECOM PARISTECH   (France)

^c YAHOO RESEARCH   (United States)

Author keywords

KL divergence; Stochastic multi armed bandits; Subset selection

Indexed keywords

ARTIFICIAL INTELLIGENCE; SOFTWARE ENGINEERING;

ADAPTIVE SAMPLING; CHERNOFF INFORMATION; CONFIDENCE INTERVAL; INFORMATION COMPLEXITY; KL-DIVERGENCE; MULTI ARMED BANDIT; SUBSET SELECTION;

STOCHASTIC SYSTEMS;

EID: 84898028877     PISSN: 15324435     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Conference Paper

References (20)

1. J-Y. Audibert, S. Bubeck, and R. Munos. Best arm identification in multi-armed bandits. In Conference on Learning Theory (COLT), 2010.
2. P. Auer, N. Cesa-Bianchi, and P. Fischer. Finite-time analysis of the multiarmed bandit problem. Machine Learning, 47(2): 235-256, 2002.
3. S. Bubeck, R. Munos, and G. Stoltz. Pure exploration in finitely armed and continuous armed bandits. Theoretical Computer Science 412, 1832-1852, 412: 1832-1852, 2011.
4. S. Bubeck, T. Wang, and N. Viswanathan. Multiple identifications in multi-armed bandits. In International Conference on Machine Learning (ICML). To appear, 2013.
5. O. Cappé, A. Garivier, O-A. Maillard, R. Munos, and G. Stoltz. Kullback-Leibler upper confidence bounds for optimal sequential allocation. to appear in Annals of Statistics, 2013.
6. T. Cover and J. Thomas. Elements of Information Theory (2nd Edition). Wiley, 2006.
7. E. Even-Dar, S. Mannor, and Y. Mansour. Action elimination and stopping conditions for the multi-armed bandit and reinforcement learning problems. Journal of Machine Learning Research, 7: 1079-1105, 2006.
8. V. Gabillon, M. Ghavamzadeh, and A. Lazaric. Best arm identification: A unified approach to fixed budget and fixed confidence. In Neural Information and Signal Processing (NIPS), 2012.
9. A. Garivier and O. Cappé. The KL-UCB algorithm for bounded stochastic bandits and beyond. In Conference on Learning Theory (COLT), 2011.
10. V. Heidrich-Meisner and C. Igel. Hoeffding and Bernstein races for selecting policies in evolutionary direct policy search. In International Conference on Learning Theorey (ICML), 2009.
11. S. Kalyanakrishnan. Learning Methods for Sequential Decision Making with Imperfect Representations. PhD thesis, Departement of Computer Science, The University of Texas at Austin, 2011.
12. S. Kalyanakrishnan and P. Stone. Efficient selection in multiple bandit arms: Theory and practice. In International Conference on Machine Learning (ICML), 2010.
13. S. Kalyanakrishnan, A. Tewari, P. Auer, and P. Stone. PAC subset selection in stochastic multi-armed bandits. In International Conference on Machine Learning (ICML), 2012.
14. E. Kaufmann, N. Korda, and R. Munos. Thompson sampling: an asymptotically optimal finite-time analysis. In Algorithmic Learning Theory (ALT), 2012.
15. T.L. Lai and H. Robbins. Asymptotically efficient adaptive allocation rules. Advances in Applied Mathematics, 6(1): 4-22, 1985.
16. O-A. Maillard, R. Munos, and G. Stoltz. A finite-time analysis of multi-armed bandits problems with Kullback-Leibler divergences. In Conference On Learning Theory (COLT), 2011.
17. S. Mannor and J. Tsitsiklis. The sample complexity of exploration in the multi-armed bandit problem. Journal of Machine Learning Research, pages 623-648, 2004.
18. O. Maron and A. Moore. The racing algorithm: Model selection for lazy learners. Artificial Intelligence Review, 11(1-5): 113-131, 1997.
19. V. Mnih, C. Szepesvári, and J.-Y. Audibert. Empirical Bernstein stopping. In International Conference on Machine Learning (ICML), 2008.
20. W.R. Thompson. On the likelihood that one unknown probability exceeds another in view of the evidence of two samples. Biometrika, 25: 285-294, 1933.