Options
Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities
Auteur(s)
Date de parution
2019
In
Computing Research Repository (CoRR)
Vol.
1905.12425
Résumé
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.
Identifiants
Type de publication
journal article
Dossier(s) à télécharger
