Options
Dimitrakakis, Christos
Nom
Dimitrakakis, Christos
Affiliation principale
Fonction
Professor
Email
christos.dimitrakakis@unine.ch
Identifiants
Résultat de la recherche
Voici les éléments 1 - 1 sur 1
- PublicationAccès libreNear-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities(2019)
;Aristide Tossou ;Debabrota BasuWe study model-based reinforcement learning in an unknown finite communicating Markov decision process. We propose a simple algorithm that leverages a variance based confidence interval. We show that the proposed algorithm, UCRL-V, achieves the optimal regret O~(DSAT−−−−−−√) up to logarithmic factors, and so our work closes a gap with the lower bound without additional assumptions on the MDP. We perform experiments in a variety of environments that validates the theoretical bounds as well as prove UCRL-V to be better than the state-of-the-art algorithms.