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

Abstract: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. The proposed estimators, 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 product Riemannian manifold. This geometric perspective on the parameter space naturally introduces Riemannian optimization into the policy-evaluation step of standard policy-iteration (PI) frameworks. Moreover, rigorous theoretical analysis establishes performance bounds on Q-function estimation error under the proposed PI scheme. Supporting numerical tests show that 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.

Machine Learning (cs.LG)

arXiv:2512.18763 [cs.LG]

(or arXiv:2512.18763v2 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2512.18763 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.