Skip to yearly menu bar Skip to main content


Poster

Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs

Max Simchowitz · Kevin Jamieson

East Exhibition Hall B, C #203

Keywords: [ Markov Decision Processes ] [ Reinforcement Learning and Planning ] [ Learning Theory ] [ Algorithms -> Active Learning; Algorithms -> Bandit Algorithms; Theory ]


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 $\widetilde{\mathcal{O}}(\sqrt{HSAT})$-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.

Live content is unavailable. Log in and register to view live content