Improved Algorithms for Misspecified Linear Markov Decision Processes
Abstract
For the misspecified linear Markov decision process (MLMDP) model of Jin et al. [2020], we propose an algorithm with three desirable properties. (P1) Its regret after episodes scales as , where is the degree of misspecification and is a user-specified error tolerance. (P2) Its space and per-episode time complexities remain bounded as . (P3) It does not require as input. To our knowledge, this is the first algorithm satisfying all three properties. For concrete choices of , we also improve existing regret bounds (up to log factors) while achieving either (P2) or (P3) (existing algorithms satisfy neither). At a high level, our algorithm generalizes (to MLMDPs) and refines the Sup-Lin-UCB algorithm, which Takemura et al. [2021] recently showed satisfies (P3) for contextual bandits. We also provide an intuitive interpretation of their result, which informs the design of our algorithm.
Cite
@article{arxiv.2109.05546,
title = {Improved Algorithms for Misspecified Linear Markov Decision Processes},
author = {Daniel Vial and Advait Parulekar and Sanjay Shakkottai and R. Srikant},
journal= {arXiv preprint arXiv:2109.05546},
year = {2022}
}
Comments
This version adds an intuitive explanation in Section 3