Sparse Ergodic Control with Control-Dependent Noise via Physics-Informed Neural Networks
Electronics · 13.07.2026 · 15 (14) · 3073
DOI: 10.3390/electronics15143073 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 13.07.2026. Verfasst von Zhaosheng Xu und 5 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Sparse ergodic control provides a natural framework for long-run stochastic decision-making under resource constraints. Existing formulations, however, are typically restricted to control-affine systems with control-independent diffusion. When the diffusion coefficient depends explicitly on the control input, the associated ergodic Hamilton–Jacobi–Bellman (HJB) equation becomes non-separable through the term trax, u∇2V, so classical arguments based on control-affine separability no longer apply directly. In this work, we study sparse ergodic control of stochastic systems with control-dependent diffusion and nonlinear dynamics within a viscosity-solution and learning-based framework. To address the discontinuous ℓ0-type sparsity penalty, we introduce smooth non-convex sparsity approximations that preserve differentiability while retaining sparse threshold behavior. Within a viscosity-solution framework, we analyze the existence and uniqueness properties of the associated ergodic pair and establish localized approximation error estimates for the smooth approximation. We further characterize a quasi-threshold sparse structure of the resulting optimal feedback policies in non-affine stochastic systems with control-dependent noise. On the computational side, we develop a Physics-Informed Neural Network (PINN)-based solver with adaptive residual-driven sampling for high-dimensional sparse ergodic HJB equations, together with a distributed monotone-inspired iterative scheme for weakly coupled multi-agent systems. Numerical experiments on multi-robot swarm navigation and renewable-integrated smart-grid control demonstrate that the proposed methods produce sparse control policies while preserving stable long-run performance under stochastic disturbances.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Xu, Z., Liu, J., Ang, M. C., Liao, Z., Ng, K. W., & Kor, A. (2026). Sparse Ergodic Control with Control-Dependent Noise via Physics-Informed Neural Networks. Electronics, 15(14), 3073. https://doi.org/10.3390/electronics15143073
Vancouver
Xu Z, Liu J, Ang MC, Liao Z, Ng KW, Kor A. Sparse Ergodic Control with Control-Dependent Noise via Physics-Informed Neural Networks. Electronics. 2026;15(14):3073. doi:10.3390/electronics15143073
BibTeX
@article{Xu2026,
author = {Xu, Zhaosheng and Liu, Jianbang and Ang, Mei Choo and Liao, Zhongming and Ng, Kok Weng and Kor, Ah-Lian},
title = {Sparse Ergodic Control with Control-Dependent Noise via Physics-Informed Neural Networks},
journal = {Electronics},
year = {2026},
volume = {15},
number = {14},
pages = {3073},
doi = {10.3390/electronics15143073}
}
EUVIMED