Provably adaptive reinforcement learning in metric spaces
Machine Learning
2021-10-22 v2 Machine Learning
Abstract
We study reinforcement learning in continuous state and action spaces endowed with a metric. We provide a refined analysis of a variant of the algorithm of Sinclair, Banerjee, and Yu (2019) and show that its regret scales with the \emph{zooming dimension} of the instance. This parameter, which originates in the bandit literature, captures the size of the subsets of near optimal actions and is always smaller than the covering dimension used in previous analyses. As such, our results are the first provably adaptive guarantees for reinforcement learning in metric spaces.
Cite
@article{arxiv.2006.10875,
title = {Provably adaptive reinforcement learning in metric spaces},
author = {Tongyi Cao and Akshay Krishnamurthy},
journal= {arXiv preprint arXiv:2006.10875},
year = {2021}
}
Comments
Published in NeurIPS 2020. This version fixes a bug in the published version