Kernel-Based Reinforcement Learning: A Finite-Time Analysis
Abstract
We consider the exploration-exploitation dilemma in finite-horizon reinforcement learning problems whose state-action space is endowed with a metric. We introduce Kernel-UCBVI, a model-based optimistic algorithm that leverages the smoothness of the MDP and a non-parametric kernel estimator of the rewards and transitions to efficiently balance exploration and exploitation. For problems with episodes and horizon , we provide a regret bound of , where is the covering dimension of the joint state-action space. This is the first regret bound for kernel-based RL using smoothing kernels, which requires very weak assumptions on the MDP and has been previously applied to a wide range of tasks. We empirically validate our approach in continuous MDPs with sparse rewards.
Cite
@article{arxiv.2004.05599,
title = {Kernel-Based Reinforcement Learning: A Finite-Time Analysis},
author = {Omar Darwiche Domingues and Pierre Ménard and Matteo Pirotta and Emilie Kaufmann and Michal Valko},
journal= {arXiv preprint arXiv:2004.05599},
year = {2022}
}
Comments
Update following the publication in ICML 2021, including fixed typos