Gaussian-Mixture-Model Q-Functions for Policy Iteration in Reinforcement Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Vu, Minh, Slavakis, Konstantinos
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915688771223552
author Vu, Minh
Slavakis, Konstantinos
author_facet Vu, Minh
Slavakis, Konstantinos
contents Unlike their conventional use as estimators of probability density functions in reinforcement learning (RL), this paper introduces a novel function-approximation role for Gaussian mixture models (GMMs) as direct surrogates for Q-function losses. These parametric models, termed GMM-QFs, possess substantial representational capacity, as they are shown to be universal approximators over a broad class of functions. They are further embedded within Bellman residuals, where their learnable parameters -- a fixed number of mixing weights, together with Gaussian mean vectors and covariance matrices -- are inferred from data via optimization on a Riemannian manifold. This geometric perspective on the parameter space naturally incorporates Riemannian optimization into the policy-evaluation step of standard policy-iteration frameworks. Rigorous theoretical results are established, and supporting numerical tests show that, even without access to experience data, GMM-QFs deliver competitive performance and, in some cases, outperform state-of-the-art approaches across a range of benchmark RL tasks, all while maintaining a significantly smaller computational footprint than deep-learning methods that rely on experience data.
format Preprint
id arxiv_https___arxiv_org_abs_2512_18763
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gaussian-Mixture-Model Q-Functions for Policy Iteration in Reinforcement Learning
Vu, Minh
Slavakis, Konstantinos
Machine Learning
Unlike their conventional use as estimators of probability density functions in reinforcement learning (RL), this paper introduces a novel function-approximation role for Gaussian mixture models (GMMs) as direct surrogates for Q-function losses. These parametric models, termed GMM-QFs, possess substantial representational capacity, as they are shown to be universal approximators over a broad class of functions. They are further embedded within Bellman residuals, where their learnable parameters -- a fixed number of mixing weights, together with Gaussian mean vectors and covariance matrices -- are inferred from data via optimization on a Riemannian manifold. This geometric perspective on the parameter space naturally incorporates Riemannian optimization into the policy-evaluation step of standard policy-iteration frameworks. Rigorous theoretical results are established, and supporting numerical tests show that, even without access to experience data, GMM-QFs deliver competitive performance and, in some cases, outperform state-of-the-art approaches across a range of benchmark RL tasks, all while maintaining a significantly smaller computational footprint than deep-learning methods that rely on experience data.
title Gaussian-Mixture-Model Q-Functions for Policy Iteration in Reinforcement Learning
topic Machine Learning
url https://arxiv.org/abs/2512.18763