The reviewed record of science sign in
Pith

arxiv: 2410.23498 · v1 · pith:5UF652YZ · submitted 2024-10-30 · cs.LG · cs.AI· stat.ML

Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:5UF652YZrecord.jsonopen to challenge →

classification cs.LG cs.AIstat.ML
keywords functionkernel-basedalgorithmsettingapproximationaverageexpectedlearning
0
0 comments X
read the original abstract

Reinforcement learning utilizing kernel ridge regression to predict the expected value function represents a powerful method with great representational capacity. This setting is a highly versatile framework amenable to analytical results. We consider kernel-based function approximation for RL in the infinite horizon average reward setting, also referred to as the undiscounted setting. We propose an optimistic algorithm, similar to acquisition function based algorithms in the special case of bandits. We establish novel no-regret performance guarantees for our algorithm, under kernel-based modelling assumptions. Additionally, we derive a novel confidence interval for the kernel-based prediction of the expected value function, applicable across various RL problems.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.