Towards optimal algorithms for multi-player bandits without collision sensing information - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Towards optimal algorithms for multi-player bandits without collision sensing information

Résumé

We propose a novel algorithm for multi-player multi-armed bandits without collision sensing information. Our algorithm circumvents two problems shared by all state-of-the-art algorithms: it does not need as an input a lower bound on the minimal expected reward of an arm, and its performance does not scale inversely proportionally to the minimal expected reward. We prove a theoretical regret upper bound to justify these claims. We complement our theoretical results with numerical experiments, showing that the proposed algorithm outperforms state-of-the-art.
Fichier principal
Vignette du fichier
huang22a.pdf (323 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03942518 , version 1 (17-01-2023)

Identifiants

Citer

Wei Huang, Richard Combes, Cindy Trinh. Towards optimal algorithms for multi-player bandits without collision sensing information. COLT 2022: 35th Conference on Learning Theory, Jul 2022, London, United Kingdom. pp.1990-2012. ⟨hal-03942518⟩
29 Consultations
29 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More