Saved in:
Bibliographic Details
Main Authors: Wang, Junkai, Zhao, Yuxuan, Zhou, Mi, Zhang, Fumin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.19398
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916920558616576
author Wang, Junkai
Zhao, Yuxuan
Zhou, Mi
Zhang, Fumin
author_facet Wang, Junkai
Zhao, Yuxuan
Zhou, Mi
Zhang, Fumin
contents The region of attraction is a key metric of the robustness of systems. This paper addresses the numerical solution of the generalized Zubov's equation, which produces a special Lyapunov function characterizing the robust region of attraction for perturbed systems. To handle the highly nonlinear characteristic of the generalized Zubov's equation, we propose a physics-informed neural network framework that employs a policy iteration training scheme with rollout to approximate the viscosity solution. In addition to computing the optimal disturbance during the policy improvement process, we incorporate neural network-generated value estimates as anchor points to facilitate the training procedure to prevent singularities in both low- and high-dimensional systems. Numerical simulations validate the effectiveness of the proposed approach.
format Preprint
id arxiv_https___arxiv_org_abs_2508_19398
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Robust Regions of Attraction Using Rollout-Enhanced Physics-Informed Neural Networks with Policy Iteration
Wang, Junkai
Zhao, Yuxuan
Zhou, Mi
Zhang, Fumin
Systems and Control
The region of attraction is a key metric of the robustness of systems. This paper addresses the numerical solution of the generalized Zubov's equation, which produces a special Lyapunov function characterizing the robust region of attraction for perturbed systems. To handle the highly nonlinear characteristic of the generalized Zubov's equation, we propose a physics-informed neural network framework that employs a policy iteration training scheme with rollout to approximate the viscosity solution. In addition to computing the optimal disturbance during the policy improvement process, we incorporate neural network-generated value estimates as anchor points to facilitate the training procedure to prevent singularities in both low- and high-dimensional systems. Numerical simulations validate the effectiveness of the proposed approach.
title Learning Robust Regions of Attraction Using Rollout-Enhanced Physics-Informed Neural Networks with Policy Iteration
topic Systems and Control
url https://arxiv.org/abs/2508.19398