Model-Free Semi-Global Output Regulation for Discrete-Time Linear Systems Subject to Input Amplitude Saturation


In this paper, a data-driven method is developed based on off-policy reinforcement learning to solve the semi-global output regulation of discrete-time linear systems with input saturation. Algebraic Riccati equation based method is used to design a family of state feedback laws for the constrained output regulation problem. In contrast to the existing methods, complete knowledge of the system dynamics is no longer required in this paper. Instead, the data collected from on-line is efficiently utilized to obtain the adaptive optimal control policy. It is shown that the presented method can find feedback control inputs with constraint of amplitude saturation and the ability to stabilize a given linear system with all its poles inside or on the unit circle. Finally, a simulation example is carried out to demonstrate the conclusions of the whole paper.

Meeting Name

33rd Youth Academic Annual Conference of Chinese Association of Automation, YAC 2018 (2018: May 18-20, Nanjing, China)


Electrical and Computer Engineering


This work was supported in part by the National Natural Science Foundation of China (NSFC Grant under No. 61333002 and No. 61473032), Fundamental Research Funds for the China Central Universities of USTB (FRF-GF-17- B48), the Mary K. Finley Endowment, the Missouri S&T Intelligent Systems Center and the National Science Foundation.

Keywords and Phrases

Feedback control; Linear systems; Optimal control systems; Reinforcement learning; Riccati equations; State feedback; Adaptive optimal control; Algebraic Riccati equations; Amplitude saturation; Discrete time linear systems; Input saturation; Model free; Output regulation; Output regulation problem; Algebra

International Standard Book Number (ISBN)


Document Type

Article - Conference proceedings

Document Version


File Type





© 2018 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.