Open problem: Regret bounds for thompson sampling

Journal of Machine Learning Research

Volumn 23, Issue , 2012, Pages

  Li, Lihong ^a   Chapelle, Olivier ^a,b  

^a YAHOO RESEARCH   (United States)

^b Criteo   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; SOFTWARE ENGINEERING;

BALANCING EXPLORATION AND EXPLOITATIONS; BAYESIAN APPROACHES; EMPIRICAL STUDIES; FINDING SOLUTIONS; PARAMETRIC MODELS; REAL-WORLD PROBLEM; REGRET BOUNDS; THOMPSON SAMPLINGS;

BAYESIAN NETWORKS;

EID: 84900037074     PISSN: 15324435     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Conference Paper

References (13)

1. A. Agarwal, M. Dud́ik, S. Kale, J. Langford, and R. E. Schapire. Contextual bandit learning under the realizability assumption. In AISTATS, 2012.
2. S. Agrawal and N. Goyal. Analysis of Thompson sampling for the multi-armed bandit problem. CoRR, abs/1111.1797, 2011.
3. P. Auer, N. Cesa-Bianchi, Y. Freund, and R. E. Schapire. The nonstochastic multiarmed bandit problem. SIAM Journal on Computing, 32(1):48-77, 2002.
4. O. Chapelle and L. Li. An empirical evaluation of Thompson sampling. In Advances in Neural Information Processing Systems 24, pages 2249-2257, 2012.
5. M. Dud́ik, D. Hsu, S. Kale, N. Karampatziakis, J. Langford, L. Reyzin, and T. Zhang. Efficient optimal learning for contextual bandits. In UAI, pages 169-178, 2011.
6. T. Graepel, J. Q. Candela, T. Borchert, and R. Herbrich. Web-scale Bayesian click-through rate prediction for sponsored search advertising in Microsoft's Bing search engine. In ICML, pages 13-20, 2010.
7. O.-C. Granmo. Solving two-armed bernoulli bandit problems using a bayesian learning automaton. Int'l Journal of Intellient Computing and Cybernetics, 3(2):207-234, 2010.
8. T.L. Lai and H. Robbins. Asymptotically efficient adaptive allocation rules. Advances in Applied Mathematics, 6:4-22, 1985.
9. J. Langford and T. Zhang. The epoch-greedy algorithm for contextual multi-armed bandits. In Advances in Neural Information Processing Systems 20, pages 1096-1103, 2008.
10. B. C. May and D.S. Leslie. Simulation studies in optimistic Bayesian sampling in contextual-bandit problems. Technical Report 11:02, Dept. of Mathematics, Univ. of Bristol, 2011.
11. B. C. May, N. Korda, A. Lee, and D.S. Leslie. Optimistic Bayesian sampling in contextual-bandit problems. Technical Report 11:01, Dept. of Mathematics, Univ. of Bristol, 2011.
12. S. Scott. A modern Bayesian look at the multi-armed bandit. Applied Stochastic Models in Business and Industry, 26:639-658, 2010.
13. W. R. Thompson. On the likelihood that one unknown probability exceeds another in view of the evidence of two samples. Biometrika, 25(3-4):285-294, 1933.