Robust Actor-Critic Learning for Continuous-Time Nonlinear Systems With Unmodeled Dynamics

This article considers the robust optimal control problem for a class of nonlinear systems in the presence of unmodeled dynamics. An adaptive optimal controller is designed using the online actor-critic learning and is robustified against unmodeled dynamics. To deal with unmodeled dynamics, an auxil...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on fuzzy systems 2022-06, Vol.30 (6), p.2101-2112
Main Authors: Yang, Yongliang, Gao, Weinan, Modares, Hamidreza, Xu, Cheng-Zhong
Format: Article
Language:English
Subjects:
Closed loops
Control systems design
Dynamical systems
Fuzzy logic
Heuristic algorithms
Input-to-state stability
Learning
Nonlinear dynamical systems
Nonlinear systems
Optimal control
Power system dynamics
robust actor–critic learning
Robust control
Stability criteria
Uncertainty
unmodeled dynamics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This article considers the robust optimal control problem for a class of nonlinear systems in the presence of unmodeled dynamics. An adaptive optimal controller is designed using the online actor-critic learning and is robustified against unmodeled dynamics. To deal with unmodeled dynamics, an auxiliary signal with the system state as its input signal is designed to capture the input-to-state stability. In addition to the critic network for value function approximation, a novel robustifying term is developed and introduced into the actor network to ensure robustness during the learning process. It is shown that both the actor and the critic weights learning converge to their optimal values while guaranteeing the boundedness of all the signals in the closed loop. Simulation examples are conducted to verify the efficacy of the presented scheme.
ISSN:1063-6706
1941-0034
DOI:10.1109/TFUZZ.2021.3075501