MMODELYST
Papers/Improved Model-based Reinforcement Learning with Smooth Kernels
PAP

Improved Model-based Reinforcement Learning with Smooth Kernels

May 8, 2026

arXiv
Abstract

For continuous state-action space scenarios, classical reinforcement learning (RL) theory predominantly focuses on low-rank Markov decision processes (MDPs), which provide sample-efficient guarantees at the expense of restrictive structural assumptions. Kernel smoothing model-based approaches offer a promising alternative paradigm that instead leverages the smoothness of the MDP and employs non-parametric kernel smoothing estimates of transition dynamics. This paper proposes a new kernel-smoothing model-based approach for online reinforcement learning in finite-horizon settings under Lipschitz continuity assumptions on the MDP. By incorporating a Bernstein-style exploration bonus into the kernel smoothing framework, our method achieves a regret bound which improves upon the state-of-the-art regret bound in its dependence on the horizon. The theoretical advancement relies on a delicate analysis of the synergy between Bernstein-style bonuses and kernel smoothing, where a new tight Bernstein-type concentration inequality for martingales may be of independent interest.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Kun Long, Yuqiang Li, Xianyi Wu
Your notes (browser-local)
saved
arXiv:2605.07218