Global H∞ Output Regulation of Nonlinear Systems via Output-Feedback Reinforcement Learning
成果类型：
Article
署名作者：
Li, Shaobao; Wang, Yuxiang; Zhang, Yuguang; Luo, Xiaoyuan; Wang, Juan; Xinping, Guan
署名单位：
Yanshan University; Shanghai Jiao Tong University
刊物名称：
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
ISSN/ISSBN：
0018-9286
DOI：
10.1109/TAC.2025.3621992
发表日期：
2026
关键词：
摘要：
This article addresses the H-infinity output regulation problem of affine nonlinear systems with unmeasurable states and completely unknown dynamics. The H-infinity output regulation problem is formulated into a two-player zero-sum differential game problem with the control input and disturbance being the two adversary players. A model-based global state-feedback optimal solution to the H-infinity output regulation problem is presented by solving a Hamilton-Jacobi-Isaacs (HJI) equation, and a state-feedback reinforcement learning (RL) algorithm is proposed to solve the HJI equation without knowledge of system dynamics. A linear data-driven observer is designed to estimate the unmeasurable states and a novel output-feedback RL algorithm is developed based on the state-feedback RL framework by employing a criticactor-disturbance neural network with a hidden layer. The salient found of this work is that, under the proposed output-feedback RL algorithm, the closed-loop system can reach globally stable. A numerical example is provided to demonstrate the effectiveness of the proposed solution