On Explore-Then-Commit Strategies - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

On Explore-Then-Commit Strategies

Résumé

We study the problem of minimising regret in two-armed bandit problems with Gaussian rewards. Our objective is to use this simple setting to illustrate that strategies based on an exploration phase (up to a stopping time) followed by exploitation are necessarily suboptimal. The results hold regardless of whether or not the difference in means between the two arms is known. Besides the main message, we also refine existing deviation inequalities, which allow us to design fully sequential strategies with finite-time regret guarantees that are (a) asymptotically optimal as the horizon grows and (b) order-optimal in the minimax sense. Furthermore we provide empirical evidence that the theory also holds in practice and discuss extensions to non-gaussian and multiple-armed case.
Fichier principal
Vignette du fichier
nips_final.pdf (753.95 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01322906 , version 1 (28-05-2016)
hal-01322906 , version 2 (14-11-2016)

Identifiants

Citer

Aurélien Garivier, Emilie Kaufmann, Tor Lattimore. On Explore-Then-Commit Strategies. NIPS, Dec 2016, Barcelona, Spain. ⟨hal-01322906v2⟩
358 Consultations
236 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More