Kullback-Leibler Upper Confidence Bounds for Optimal Sequential Allocation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Annals of Statistics Year : 2013

Kullback-Leibler Upper Confidence Bounds for Optimal Sequential Allocation

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 (1979), 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 (1985) and Burnetas and Katehakis (1996), 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.
Fichier principal
Vignette du fichier
klucb.pdf (546.24 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00738209 , version 1 (03-10-2012)
hal-00738209 , version 2 (21-03-2013)

Identifiers

Cite

Olivier Cappé, Aurélien Garivier, Odalric-Ambrym Maillard, Rémi Munos, Gilles Stoltz. Kullback-Leibler Upper Confidence Bounds for Optimal Sequential Allocation. Annals of Statistics, 2013, 41 (3), pp.1516-1541. ⟨10.1214/13-AOS1119⟩. ⟨hal-00738209v2⟩
1506 View
2798 Download

Altmetric

Share

Gmail Facebook X LinkedIn More