A novel neural network (NN) -based output feedback controller with magnitude constraints is designed to deliver a desired tracking performance for a class of multi-input-multi-output (MIMO) discrete-time strict feedback nonlinear systems. Reinforcement learning in discrete time is proposed for the output feedback controller, which uses three NN: 1) a NN observer to estimate the system states with the input-output data; 2) a critic NN to approximate certain strategic utility function; and 3) an action NN to minimize both the strategic utility function and the unknown dynamics estimation errors. The magnitude constraints are manifested as saturation nonlinearities in the output feedback controller design. Using the Lyapunov approach, the uniformly ultimate boundedness (UUB) of the state estimation errors, the tracking errors and weight estimates is shown.
P. He and J. Sarangapani, "Reinforcement Learning-Based Output Feedback Control of Nonlinear Systems with Input Constraints," IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 35, no. 1, pp. 150-154, Institute of Electrical and Electronics Engineers (IEEE), Feb 2005.
The definitive version is available at http://dx.doi.org/10.1109/TSMCB.2004.840124
Electrical and Computer Engineering
Keywords and Phrases
Reinforcement learning; , Neural networks (NNs); Output feedback control
Library of Congress Subject Headings
Neural networks (Computer science)
Nonlinear control theory
International Standard Serial Number (ISSN)
Article - Journal
© 2004 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.