Convergence Analysis of Adaptive Critic based Optimal Control

Author

Xin Liu, Missouri University of Science and TechnologyFollow
S. N. Balakrishnan, Missouri University of Science and TechnologyFollow

Abstract

Adaptive critic based neural networks have been found to be powerful tools in solving various optimal control problems. The adaptive critic approach consists of two neural networks which output the control values and the Lagrangian multipliers associated with optimal control. These networks are trained successively and when the outputs of the two networks are mutually consistent and satisfy the differential constraints, the controller network output produces optimal control. In this paper, we analyze the mechanics of convergence of the network solutions. We establish the necessary conditions for the network solutions to converge and show that the converged solution is optimal.

Recommended Citation

X. Liu and S. N. Balakrishnan, "Convergence Analysis of Adaptive Critic based Optimal Control," Proceedings of the American Control Conference, vol. 3, pp. 1929 - 1933, Institute of Electrical and Electronics Engineers, Dec 2000.

Department(s)

Nuclear Engineering and Radiation Science

Second Department

Mechanical and Aerospace Engineering

International Standard Serial Number (ISSN)

0743-1619

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2024 Institute of Electrical and Electronics Engineers, All rights reserved.

Publication Date

01 Dec 2000