An asymptotically optimal bandit algorithm for bounded support models

COLT 2010 - The 23rd Conference on Learning Theory

Volumn , Issue , 2010, Pages 67-79

  Honda, Junya ^a   Takemura, Akimichi ^a  

^a UNIVERSITY OF TOKYO   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

ASYMPTOTIC BOUNDS; ASYMPTOTICALLY OPTIMAL; BANDIT PROBLEMS; BOUNDED SUPPORT; CONVEX OPTIMIZATION TECHNIQUES; EXPLORATION AND EXPLOITATION; MULTI-ARMED BANDIT PROBLEM; MULTIPLE ARMS;

CONVEX OPTIMIZATION; REINFORCEMENT LEARNING;

PROBABILITY;

EID: 84898077171     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (21)

1. Agrawal, R. (1995). The continuum-armed bandit problem. SIAM J. Control Optim., 33, 1926-1951.
2. Auer, P., Cesa-Bianchi, N., & Fischer, P. (2002). Finite-time analysis of the multiarmed bandit problem. Machine Learning, 47, 235-256.
3. Auer, P., Cesa-Bianchi, N., Freund, Y., & Schapire, R. E. (2003). The nonstochastic multiarmed bandit problem. SIAM J. Comput., 32, 48-77.
4. Boyd, S., & Vandenberghe, L. (2004). Convex optimization. Cambridge University Press.
5. Burnetas, A. N., & Katehakis, M. N. (1996). Optimal adaptive policies for sequential allocation problems. Adv. Appl. Math., 17, 122-142.
6. Dembo, A., & Zeitouni, O. (1998). Large deviations techniques and applications, Vol. 38 of Applications of Mathematics. New York: Springer-Verlag. Second edition.
7. Even-Dar, E., Mannor, S., & Mansour, Y. (2002). Pac bounds for multi-armed bandit and markov decision processes. Proceedings of COLT 2002 (pp. 255-270). London, UK: Springer-Verlag.
8. Fiacco, A. V. (1983). Introduction to sensitivity and stability analysis in nonlinear programming. New York: Academic Press.
9. Gittins, J. C. (1989). Multi-armed bandit allocation indices. Wiley-Interscience Series in Systems and Optimization. Chichester: John Wiley & Sons Ltd. With a foreword by Peter Whittle.
10. Honda, J., & Takemura, A. (2010). An asymptotically optimal policy for finite support models in the multi-armed bandit problem. Submitted to Machine Learning, arXiv:0905.2776v3.
11. Ishikida, T., & Varaiya, P. (1994). Multi-armed bandit problem revisited. J. Optim. Theory Appl., 83, 113-154.
12. Kleinberg, R. (2005). Nearly tight bounds for the continuum-armed bandit problem. Proceedings of NIPS 2005 (pp. 697-704). MIT Press.
13. Kleinberg, R. D., Niculescu-Mizil, A., & Sharma, Y. (2008). Regret bounds for sleeping experts and bandits. Proceedings of COLT 2008 (pp. 425-436).
14. Lai, T. L., & Robbins, H. (1985). Asymptotically efficient adaptive allocation rules. Advances in Applied Mathematics, 6, 4-22.
15. Lamperti, J. (1996). Probability; a survey of the mathematical theory. Wiley Series in Probability Statistics. New York: John Wiley & Sons Ltd. Second edition.
16. Meuleau, N., & Bourgine, P. (1999). Exploration of multi-state environments: Local measures and back-propagation of uncertainty. Machine Learning, 35, 117-154.
17. Pinsker, M. S. (1964). Information and information stability of random variables and processes (transl.). San Francisco: Holden Day.
18. Rockafellar, R. T. (1970). Convex analysis (Princeton Mathematical Series). Princeton University Press.
19. Strens, M. (2000). A bayesian framework for reinforcement learning. Proceedings of ICML 2000 (pp. 943-950). Morgan Kaufmann, San Francisco, CA.
20. Vermorel, J., & Mohri, M. (2005). Multi-armed bandit algorithms and empirical evaluation. Proceedings of ECML 2005 (pp. 437-448). Porto, Portugal: Springer.
21. Yakowitz, S., & Lowe, W. (1991). Nonparametric bandit methods. Ann. Oper. Res., 28, 297-312.