KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints
KL-UCB-switch : un nouvel algorithme de bandit asymptotiquement optimal et minimax optimal
Résumé
In the context of K–armed stochastic bandits with distribution only assumed to be supported by [0, 1], we introduce a new algorithm, KL-UCB-switch, and prove that is enjoys simultaneously a distribution-free regret bound of optimal order √ KT and a distribution-dependent regret bound of optimal order as well, that is, matching the κ ln T lower bound by Lai and Robbins (1985) and Burnetas and Katehakis (1996).
Fichier principal
KL-UCB+-Garivier-Hadiji-Menard-Stoltz.pdf (494.9 Ko)
Télécharger le fichier
KL-UCB+-Garivier-Hadiji-Menard-Stoltz.aux (21.11 Ko)
Télécharger le fichier
KL-UCB+-Garivier-Hadiji-Menard-Stoltz.synctex.gz (437.69 Ko)
Télécharger le fichier
Origine | Fichiers produits par l'(les) auteur(s) |
---|
Loading...