Efficient selection of multiple bandit arms: Theory and practice

ICML 2010 - Proceedings, 27th International Conference on Machine Learning

Volumn , Issue , 2010, Pages 511-518

  Kalyanakrishnan, Shivaram ^a   Stone, Peter ^a  

^a University of Texas at Austin   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

EMPIRICAL COMPARISON; MULTI ARMED BANDIT; PAC BOUNDS; SAMPLING ALGORITHM; STOCHASTIC OPTIMIZATION ALGORITHM; SUBSET SELECTION; THEORETICAL BASIS; THEORY AND PRACTICE;

LEARNING SYSTEMS; REAL VARIABLES;

RANDOM VARIABLES;

EID: 77956526578     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. Berry, Donald A. and Fristedt, Bert. Bandit problems. Chapman and Hall Ltd., 1985.
2. Chen, Chun-Hung, He, Donghai, Fu, Michail, and Lee, Loo Hay. Efficient simulation budget allocation for selecting an optimal subset. INFORMS Journal on Computing, 20(4):579-595, 2008.
3. de Boer, Pieter-Tjerk, Kroese, Dirk P., Mannor, Shie, and Rubinstein, Reuven Y. A tutorial on the cross- entropy method. Annals of Operations Research, 134(1):19-67, 2005.
4. Even-Dar, Eyal, Mannor, Shie, and Mansour, Yishay. Action elimination and stopping conditions for the multi-armed bandit and reinforcement learning problems. Journal of Mach. Learn. Research, 7: 1079-1105, 2006.
5. Heidrich-Meisner, Verena and Igel, Christian. Hoeffding and Bernstein races for selecting policies in evolutionary direct policy search. In Proc. ICML 2009, pp. 401-408. ACM, 2009.
6. Inoue, Koichiro, Chick, Stephen E., and Chen, Chun- Hung. An empirical evaluation of several methods to select the best system. ACM Transactions on Modeling and Computer Simulation, 9(4):381-407, 1999.
7. Kim, Seong-Hee and Nelson, Barry L. A fully sequential procedure for indifference-zone selection in simulation. ACM Transactions on Modeling and Computer Simulation, 11(3):251-273, 2001.
8. Koenig, Lloyd W. and Law, Averiii M. A procedure for selecting a subset of size m containing the I best of k independent normal populations, with applications to simulation. Communications in statistics. Simulation and computation, 14(3):719-734, 1985.
9. Madani, Omid and Lizotte, Daniel J. Greiner, Russell. Active model selection. In Proc. VAI 2004, pp. 357- 365. AUAI Press, 2004.
10. Mannor, Shie and Tsitsiklis, John N. The sample complexity of exploration in the multi-armed bandit problem. Journal of Mach. Learn. Research, 5: 623-648, 2004.
11. Maron, Oded and Moore, Andrew W. The racing algorithm: Model selection for lazy learners. Artificial Intelligence Review, 11(1-5):193-225, 1997.
12. Miller, Brad L. and Goldberg, David E. Genetic algorithms, selection schemes, and the varying effects of noise. Evolutionary Computation, 4(2):113-131, 1996.
13. Mnih, Volodymyr, Szepesvári, Csaba, and Audibert, Jean-Yves. Empirical Bernstein stopping. In Proc. ICML 2008, pp. 672-679. ACM, 2008.
14. Schmidt, Christian, Branke, Jürgen, and Chick, Stephen E. Integrating techniques from statistical ranking into evolutionary algorithms. In Appi, of Evolutionary Comp., volume 3907 of LNCS, pp. 752-763. Springer, 2006.
15. Whiteson, Shimon and Stone, Peter. On-line evolutionary computation for reinforcement learning in stochastic domains. In Proc. GECCO 2006, pp. 1577-1584. ACM, 2006.