Multi-bandit best arm identification

Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011

Volumn , Issue , 2011, Pages

  Gabillon, Victor ^a   Ghavamzadeh, Mohammad ^a   Lazaric, Alessandro ^a   Bubeck, Sébastien ^b  

^a INRIA   (France)

^b Princeton University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALLOCATION STRATEGY; PERFORMANCE; PROBABILITIES OF ERROR; SMALL GAPS; SYNTHETIC PROBLEM; UPPER BOUND;

EID: 85162482585     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. J.-Y. Audibert, S. Bubeck, and R. Munos. Best arm identification in multi-armed bandits. In Proceedings of the Twenty-Third Annual Conference on Learning Theory, pages 41-53, 2010.
2. Jean-YvesAudibert, RémiMunos, and Csaba Szepesvári. Tuning bandit algorithms in stochastic environments. In Marcus Hutter, Rocco Servedio, and Eiji Takimoto, editors, Algorithmic Learning Theory, volume 4754 of Lecture Notes in Computer Science, pages 150-165.Springer Berlin / Heidelberg, 2007.
3. P. Auer, N. Cesa-Bianchi, and P. Fischer. Finite-time analysis of the multi-armed bandit problem. Machine Learning, 47:235-256, 2002.
4. S. Bubeck, R. Munos, and G. Stoltz. Pure exploration in multi-armed bandit problems. In Proceedings of the Twentieth International Conference on Algorithmic Learning Theory, pages 23-37, 2009.
5. K. Deng, J. Pineau, and S. Murphy. Active learning for personalizing treatment. In IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, 2011.
6. C. Dimitrakakis and M. Lagoudakis. Rollout sampling approximate policy iteration. Machine Learning Journal, 72(3):157-171, 2008.
7. Eyal Even-Dar, ShieMannor, and YishayMansour. Action elimination and stopping conditions for the multi-armed bandit and reinforcement learning problems. Journal ofMachine Learning Research, 7:1079-1105, 2006.
8. V. Gabillon,M. Ghavamzadeh,A. Lazaric, and S. Bubeck.Multi-bandit best armidentification. Technical Report 00632523, INRIA, 2011.
9. M. Lagoudakis and R. Parr. Reinforcement learning as classification: Leveraging modern classifiers. In Proceedings of the Twentieth International Conference on Machine Learning, pages 424-431, 2003.
10. O. Maron and A. Moore. Hoeffding races: Accelerating model selection search for classification and function approximation. In Proceedings of Advances in Neural Information Processing Systems 6, 1993.
11. A. Maurer and M. Pontil. Empirical bernstein bounds and sample-variance penalization. In 22th annual conference on learning theory, 2009.
12. V. Mnih, Cs. Szepesvári, and J.-Y. Audibert. Empirical Bernstein stopping. In Proceedings of the Twenty-Fifth International Conference on Machine Learning, pages 672-679, 2008.
13. H. Robbins. Some aspects of the sequential design of experiments. Bulletin of the American Mathematics Society, 58:527-535, 1952.