Thompson Sampling: An Asymptotically Optimal Finite Time Analysis - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Thompson Sampling: An Asymptotically Optimal Finite Time Analysis

Résumé

The question of the optimality of Thompson Sampling for solving the stochastic multi-armed bandit problem had been open since 1933. In this paper we answer it positively for the case of Bernoulli rewards by providing the first finite-time analysis that matches the asymptotic rate given in the Lai and Robbins lower bound for the cumulative regret. The proof is accompanied by a numerical comparison with other optimal policies, experiments that have been lacking in the literature until now for the Bernoulli case.

Dates et versions

hal-00830033 , version 1 (04-06-2013)

Identifiants

Citer

Emilie Kaufmann, Nathaniel Korda, Rémi Munos. Thompson Sampling: An Asymptotically Optimal Finite Time Analysis. ALT 2012 - International Conference on Algorithmic Learning Theory, Oct 2012, Lyon, France. pp.199-213, ⟨10.1007/978-3-642-34106-9_18⟩. ⟨hal-00830033⟩
254 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More