Memory Bandits: a Bayesian approach for the Switching Bandit Problem - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Memory Bandits: a Bayesian approach for the Switching Bandit Problem

Résumé

The Thompson Sampling exhibits excellent results in practice and it has been shown to be asymptotically optimal. The extension of Thompson Sampling algorithm to the Switching Multi-Armed Bandit problem, proposed in [13], is a Thompson Sampling equiped with a Bayesian online change point detector [1]. In this paper, we propose another extension of this approach based on a Bayesian aggregation framework. Experiments provide some evidences that in practice, the proposed algorithm compares favorably with the previous version of Thompson Sampling for the Switching Multi-Armed Bandit Problem, while it outperforms clearly other algorithms of the state-of-the-art.
Fichier principal
Vignette du fichier
MemoryBandits_FinalVersion.pdf (935.43 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01811697 , version 1 (13-06-2018)

Identifiants

  • HAL Id : hal-01811697 , version 1

Citer

Réda Alami, Odalric Maillard, Raphael Féraud. Memory Bandits: a Bayesian approach for the Switching Bandit Problem. NIPS 2017 - 31st Conference on Neural Information Processing Systems, Dec 2017, Long Beach, United States. ⟨hal-01811697⟩
541 Consultations
670 Téléchargements

Partager

Gmail Facebook X LinkedIn More