Asymptotically Optimal Algorithms for Multiple Play Bandits with Partial Feedback - Université Paris Cité Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2016

Asymptotically Optimal Algorithms for Multiple Play Bandits with Partial Feedback

Résumé

We study a variant of the multi-armed bandit problem with multiple plays in which the user wishes to sample the m out of k arms with the highest expected rewards, but at any given time can only sample l ≤ m arms. When l = m, Thompson sampling was recently shown to be asymptotically efficient. We derive an asymptotic regret lower bound for any uniformly efficient algorithm in our new setting where may be less than m. We then establish the asymptotic optimality of Thompson sampling for Bernoulli rewards, where our proof technique differs from earlier methods even when l = m. We also prove the asymptotic optimality of an algorithm based on upper confidence bounds, KL-CUCB, for single-parameter exponential families and bounded, finitely supported rewards, a result which is new for all values of l.
Fichier principal
Vignette du fichier
combinatorial_feedback.pdf (680.97 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01338733 , version 1 (29-06-2016)
hal-01338733 , version 2 (05-11-2017)
hal-01338733 , version 3 (03-09-2019)

Identifiants

Citer

Alexander R. Luedtke, Emilie Kaufmann, Antoine Chambaz. Asymptotically Optimal Algorithms for Multiple Play Bandits with Partial Feedback. 2016. ⟨hal-01338733v1⟩
491 Consultations
371 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More