A Finite-Time Analysis of Multi-armed Bandits Problems with Kullback-Leibler Divergences
Résumé
We consider a Kullback-Leibler-based algorithm for the stochastic multi-armed bandit prob- lem in the case of distributions with nite support, whose asymptotic regret matches the lower bound of Burnetas and Katehakis (1996). Our contribution is to provide a nite-time analysis of this algorithm.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|