Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs

05/09/2019

∙

by   Max Simchowitz, et al.

∙

0

∙

share

This paper establishes that optimistic algorithms attain gap-dependent and non-asymptotic logarithmic regret for episodic MDPs. In contrast to prior work, our bounds do not suffer a dependence on diameter-like quantities or ergodicity, and smoothly interpolate between the gap dependent logarithmic-regret, and the O(√(HSAT))-minimax rate. The key technique in our analysis is a novel "clipped" regret decomposition which applies to a broad family of recent optimistic algorithms for episodic MDPs.