Timezone: »

 
Poster
Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs
Max Simchowitz · Kevin Jamieson

Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #203
in Reinforcement Learning and Planning -- Markov Decision Processes »
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.
Keywords: Reinforcement Learning and Planning -> Markov Decision Processes · Algorithms -> Active Learning; Algorithms -> Bandit Algorithms; Theory -> Learning Theory

Author Information

Max Simchowitz (Berkeley)
Kevin Jamieson (U Washington)

More from the Same Authors