Voici les éléments 1 - 1 sur 1
  • Publication
    Accès libre
    Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities
    (2019)
    Aristide Tossou
    ;
    Debabrota Basu
    ;
    We 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.