Gap-free bounds for stochastic multi-armed bandit

IFAC Proceedings Volumes (IFAC-PapersOnline)

Volumn 17, Issue 1 PART 1, 2008, Pages

  Juditsky, Anatoly ^a   Nazin, Alexander V ^a   Tsybakov, Alexander ^a   Vayatis, Nicolas ^a  

^a NONE

Author keywords

Learning theory; Randomized methods; Stochastic control

Indexed keywords

GRADIENT TYPE; INSTANTANEOUS LOSS; LEARNING THEORY; MULTI ARMED BANDIT; MULTI-ARMED BANDIT PROBLEM; RANDOMIZED DECISIONS; RANDOMIZED METHODS; STOCHASTIC CONTROL;

RISK PERCEPTION; STOCHASTIC CONTROL SYSTEMS;

PROBABILITY DISTRIBUTIONS;

EID: 79961019787     PISSN: 14746670     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.3182/20080706-5-KR-1001.2585     Document Type: Conference Paper

References (15)

1. J.Y. Audibert, Remi M., and Cs. Szepesvari. Tuning bandit algorithms in stochastic environments. In 18th International Conference on Algorithmic Learning Theory, pages 150-165, Sendai, 1-4 October 2007.
2. P. Auer, N. Cesa-Bianchi, and P. Fischer. Finite-time analysis of the multiarmed bandit problem. Machine Learning, 47:235-256, 2002a.
3. P. Auer, N. Cesa-Bianchi, Y. Freund, and R. Schapire. The nonstochastic multiarmed bandit problem. SIAM J. Comput., 32(1):48-77, 2002b.
4. A. Ben-Tal and A.S. Nemirovski. The conjugate barrier mirror descent method for non-smooth convex optimization. Minerva optimization center, Technion Institute of Technology, 1999.
5. N. Cesa-Bianchi and G. Lugosi. Prediction, Learning, and Games. Cambridge University Press, 2006.
6. A.B. Juditsky, A.V. Nazin, A.B. Tsybakov, and N. Vayatis. Recursive aggregation of estimators by the mirror descent algorithm with averaging. Problems of Information Transmission, 41(4):368-384, 2005.
7. J. Kivinen and M. Warmuth. Exponentiated gradient versus gradient descent for linear predictors. Information and Computation, 132(1):1-63, 1997.
8. T.L. Lai and H. Robbins. Asymptotic efficient adaptive allocation rules. Advances in Applied Mathematics, 6: 4-22, 1985.
9. K. Najim and A.S. Poznyak. Learning automata: theory and applications. Pergamon Press, Inc., Elmsford, NY, USA, 1994. ISBN 0-08-042024-9.
10. A.V. Nazin and A.S. Poznyak. Adaptive Choice of Variants. Nauka, Moscow, 1986.
11. A.S. Nemirovski and D.B. Yudin. Problem Complexity and Method Efficiency in Optimization. Wiley-Interscience, 1983.
12. Yu. Nesterov. Primal-dual subgradient methods for convex problems: Core discussion paper 2005/67. Louvain-la-Neuve, Belgium: Center for Operation Research and Econometrics, 2005.
13. H. Robbins. Some aspects of the sequential design of experiments. Bulletin of the American Mathematical Society, 55:527-535, 1952.
14. G. Stoltz. Incomplete information and internal regret in prediction of individual sequences. PhD thesis, Universite Paris-Sud, 2005.
15. W. Vogel. An asymptotic minimax theorem for the two armed bandit problem. The Annals of Mathematical Statistics, 31:444-451, 1960.