A Natural-Gradient Approach for Nonlinear Stochastic Systems with Parameter Uncertainty
Abstract
Controlling nonlinear stochastic systems with parametric uncertainty is a fundamental challenge in modern control theory. This paper presents a comprehensive theoretical framework for a natural-gradient method applied to polynomial chaos theory. We focus on quadratic regulator problems characterized by both parametric uncertainty and additive stochastic disturbances. We extend existing polynomial chaos approaches from linear systems to general nonlinear dynamics. To achieve this, we develop new mathematical tools to handle the complex interactions between nonlinearity, parameter uncertainty, and noise. The framework provides local convergence guarantees for the proposed natural gradient algorithm. Furthermore, it offers practical computational strategies while carefully characterizing the theoretical limitations in the nonlinear setting.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Related papers
- A Polynomial Chaos Framework for Causal Discovery in Nonlinear Uncertain SystemsLiang CaoCVPR 2026
- Making Non-Stochastic Control (Almost) as Easy as StochasticMax SimchowitzNeurIPS 2020 · 44 citations
- Learning Dynamic Causal Graphs Under Parametric Uncertainty via Polynomial Chaos ExpansionsLiang CaoICLR 2026
- Mollification Effects of Policy Gradient MethodsTao Wang, Sylvia L. Herbert, Sicun GaoICML 2024 · 2 citations
- Learning Optimal Deterministic Policies with Stochastic Policy GradientsAlessandro Montenegro, Marco Mussi, Alberto Maria Metelli, Matteo PapiniICML 2024 · 11 citations
