Bandits with Multimodal Structure - Inria - Institut national de recherche en sciences et technologies du numérique
Communication Dans Un Congrès Année : 2024

Bandits with Multimodal Structure

Hassan Saber
  • Fonction : Auteur
  • PersonId : 1265353
  • IdRef : 270696865
Odalric-Ambrym Maillard

Résumé

We consider a multi-armed bandit problem specified by a set of one-dimensional exponential family distributions endowed with a multimodal structure. The multimodal structure naturally extends the unimodal structure and appears to be underlying in quite interesting ways popular structures such as linear or Lipschitz bandits. We introduce IMED-MB, an algorithm that optimally exploits the multimodal structure, by adapting to this setting the popular Indexed Minimum Empirical Divergence (IMED) algorithm. We provide instance-dependent regret analysis of this strategy. Numerical experiments show that IMED-MB performs well in practice when assuming unimodal, polynomial or Lipschitz mean function.

Fichier principal
Vignette du fichier
2024_multimodal (1) (2).pdf (891.22 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04711994 , version 1 (27-09-2024)

Licence

Identifiants

  • HAL Id : hal-04711994 , version 1

Citer

Hassan Saber, Odalric-Ambrym Maillard. Bandits with Multimodal Structure. Reinforcement Learning Conference, Aug 2024, Amherst Massachusetts, United States. pp.39. ⟨hal-04711994⟩
0 Consultations
0 Téléchargements

Partager

More