On Gaussian approximation for entropy-regularized Q-learning with function approximation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rubtsov, Artemy, Singh, Rahul, Moulines, Eric, Naumov, Alexey, Samsonov, Sergey
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913137413849088
author Rubtsov, Artemy
Singh, Rahul
Moulines, Eric
Naumov, Alexey
Samsonov, Sergey
author_facet Rubtsov, Artemy
Singh, Rahul
Moulines, Eric
Naumov, Alexey
Samsonov, Sergey
contents In this paper, we derive rates of convergence in the high-dimensional central limit theorem for Polyak--Ruppert averaged iterates generated by entropy-regularized asynchronous Q-learning with linear function approximation and a polynomial stepsize $k^{-ω}$, $ω\in (1/2,1)$. Assuming that the sequence of observed triples $(s_k,a_k,s_{k+1})_{k \geq 0}$ forms a uniformly geometrically ergodic Markov chain, and under suitable regularity conditions for the projected soft Bellman equation, we establish a Gaussian approximation bound in the convex distance with rate of order $n^{-1/4}$, up to polylogarithmic factors in $n$, where $n$ is the number of samples used by the algorithm. To obtain this result, we combine a linearization of the soft Bellman recursion with a Gaussian approximation for the leading martingale term. Finally, we derive high-order moment bounds for the algorithm's last iterate, which might be of independent interest.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17678
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle On Gaussian approximation for entropy-regularized Q-learning with function approximation
Rubtsov, Artemy
Singh, Rahul
Moulines, Eric
Naumov, Alexey
Samsonov, Sergey
Machine Learning
In this paper, we derive rates of convergence in the high-dimensional central limit theorem for Polyak--Ruppert averaged iterates generated by entropy-regularized asynchronous Q-learning with linear function approximation and a polynomial stepsize $k^{-ω}$, $ω\in (1/2,1)$. Assuming that the sequence of observed triples $(s_k,a_k,s_{k+1})_{k \geq 0}$ forms a uniformly geometrically ergodic Markov chain, and under suitable regularity conditions for the projected soft Bellman equation, we establish a Gaussian approximation bound in the convex distance with rate of order $n^{-1/4}$, up to polylogarithmic factors in $n$, where $n$ is the number of samples used by the algorithm. To obtain this result, we combine a linearization of the soft Bellman recursion with a Gaussian approximation for the leading martingale term. Finally, we derive high-order moment bounds for the algorithm's last iterate, which might be of independent interest.
title On Gaussian approximation for entropy-regularized Q-learning with function approximation
topic Machine Learning
url https://arxiv.org/abs/2605.17678