Kullback-Leibler upper confidence bounds for optimal sequential allocation
Authors:
- Olivier CappéOCOlivier Cappé
- Aurélien GarivierAGAurélien Garivier
- Odalric-Ambrym MaillardOMOdalric-Ambrym Maillard
- Rémi MunosRMRémi Munos
- Gilles StoltzGSGilles Stoltz
Preprint
Abstract
We consider optimal sequential allocation in the context of the so-called stochastic multi-armed bandit model. We describe a generic index policy, in the sense of Gittins [J. R. Stat. Soc. Ser. B Stat. Methodol. 41 (1979) 148-177], based on upper confidence bounds of the arm payoffs computed using the Kullback-Leibler divergence. We consider two classes of distributions for which instances of this general idea are analyzed: the kl-UCB algorithm is designed for one-parameter exponential families and the empirical KL-UCB algorithm for bounded and finitely supported distributions. Our main contribution is a unified finite-time analysis of the regret of these algorithms that asymptotically matches the lower bounds of Lai and Robbins [Adv. in Appl. Math. 6 (1985) 4-22] and Burnetas and Katehakis [Adv. in Appl. Math. 17 (1996) 122-142], respectively. We also investigate the behavior of these algorithms when used with general bounded rewards, showing in particular that they provide significant improvements over the state-of-the-art.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- An asymptotically optimal policy for finite support models in the multiarmed bandit problemMachine Learning, 2011
- Multi‐Armed Bandit Allocation Indices2011
- Exploration–exploitation tradeoff using variance estimates in multi-armed banditsTheoretical Computer Science, 2009
- ASYMPTOTIC BAYES ANALYSIS FOR THE FINITE-HORIZON ONE-ARMED-BANDIT PROBLEMProbability in the Engineering and Informational Sciences, 2003
- Finite-time Analysis of the Multiarmed Bandit ProblemMachine Learning, 2002
- Theory of Point Estimation1998
- Optimal Adaptive Policies for Sequential Allocation ProblemsAdvances in Applied Mathematics, 1996
- Asymptotically efficient adaptive allocation rulesAdvances in Applied Mathematics, 1985
- Multi-Armed Bandits and the Gittins IndexJournal of the Royal Statistical Society Series B: Statistical Methodology, 1980
- Some aspects of the sequential design of experimentsBulletin of the American Mathematical Society, 1952