Title :
Reinforcement learning schemes for control design
Author :
Costa, E.F. ; Tinós, R. ; Oliveira, V.A. ; Araujo, A.F.R.
Author_Institution :
Dept. de Engenharia Eletrica, USP/EESC, Sao Carlos, Brazil
Abstract :
In this paper we consider the use of associative search and adaptive critic elements and artificial neural network for control of nonlinear and unstable plants. The reinforcement learning schemes we propose are used in the design of different controllers. An example of a magnetic suspension system is presented to illustrate the effectiveness of these controllers. We also include results of a linear optimal controller
Keywords :
adaptive control; control system synthesis; learning (artificial intelligence); neurocontrollers; nonlinear control systems; search problems; stability; adaptive critic elements; artificial neural network; associative search; control design; linear optimal controller; magnetic suspension system; nonlinear plants; reinforcement learning schemes; unstable plants; Adaptive control; Artificial neural networks; Control design; Control systems; Learning; Magnetic levitation; Nonlinear control systems; Optimal control; Programmable control; Vectors;
Conference_Titel :
American Control Conference, 1997. Proceedings of the 1997
Conference_Location :
Albuquerque, NM
Print_ISBN :
0-7803-3832-4
DOI :
10.1109/ACC.1997.609158
