2000 character limit reached
Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs
Published 9 May 2019 in cs.LG, math.OC, math.ST, stat.ML, and stat.TH | (1905.03814v2)
Abstract: 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 -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.
Paper Prompts
Sign up for free to create and run prompts on this paper.