Fast Asymptotically Optimal Algorithms for Non-Parametric Stochastic Bandits - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Fast Asymptotically Optimal Algorithms for Non-Parametric Stochastic Bandits

Fabien Pesquerel
  • Fonction : Auteur
  • PersonId : 1116626
Rémy Degenne
  • Fonction : Auteur
  • PersonId : 748911
  • IdHAL : remydegenne
Odalric-Ambrym Maillard

Résumé

We consider the problem of regret minimization in non-parametric stochastic bandits. When the rewards are known to be bounded from above, there exists asymptotically optimal algorithms, with asymptotic regret depending on an infimum of Kullback-Leibler divergences (KL). These algorithms are computationally expensive and require storing all past rewards, thus simpler but non-optimal algorithms are often used instead. We introduce several methods to approximate the infimum KL which reduce drastically the computational and memory costs of existing optimal algorithms, while keeping their regret guaranties. We apply our findings to design new variants of the MED and IMED algorithms, and demonstrate their interest with extensive numerical simulations.
Fichier principal
Vignette du fichier
5313_fast_asymptotically_optimal_al.pdf (31.2 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04337742 , version 1 (12-12-2023)

Licence

Paternité

Identifiants

  • HAL Id : hal-04337742 , version 1

Citer

Dorian Baudry, Fabien Pesquerel, Rémy Degenne, Odalric-Ambrym Maillard. Fast Asymptotically Optimal Algorithms for Non-Parametric Stochastic Bandits. NeurIPS 2023 - Thirty-seventh Conference on Neural Information Processing Systems, Dec 2023, New Orleans (Louisiana), United States. ⟨hal-04337742⟩
69 Consultations
11 Téléchargements

Partager

Gmail Facebook X LinkedIn More