Improved Analysis of UCRL2 with Empirical Bernstein Inequality

07/10/2020

∙

by   Ronan Fruit, et al.

∙

0

∙

share

We consider the problem of exploration-exploitation in communicating Markov Decision Processes. We provide an analysis of UCRL2 with Empirical Bernstein inequalities (UCRL2B). For any MDP with S states, A actions, Γ≤ S next states and diameter D, the regret of UCRL2B is bounded as O(√(DΓ S A T)).