Reinforcement learning neural network used in a tracking system controller

This paper presents a method of designing a controller for nonlinear systems based on a recurrent neural network which is trained in real time using the reinforcement learning (RL) procedure. The advantage of this method is to overcome the difficulties implied by the direct solving method of the differential models which are necessary in a classical approach. Moreover, this new technique using a real-time training is better then the MLP network controller as well as the RBF network implementation which needs both of them in a preliminary training process, based on a set of input-output data that has to be a priory experimentally determined.

[1]  R. Palmer,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[2]  Lei Guo,et al.  Adaptive Control with Recursive Identification for Stochastic Linear Systems , 1987 .

[3]  M. Corless,et al.  A new class of stabilizing controllers for uncertain dynamical systems , 1982, 1982 21st IEEE Conference on Decision and Control.

[4]  Ian R. Petersen,et al.  Linear ultimate boundedness control of uncertain dynamical systems , 1983, Autom..

[5]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[6]  Liang Li,et al.  Nonlinear adaptive prediction of nonstationary signals , 1995, IEEE Trans. Signal Process..

[7]  Bernard Friedland,et al.  Modern Control Theory for Design of Autopilots for Bank-to-Turn Missiles , 1986, 1986 American Control Conference.

[8]  O. Grigore.  RBF neural network controller for nonlinear systems , 1999, ISIE '99. Proceedings of the IEEE International Symposium on Industrial Electronics (Cat. No.99TH8465).

[9]  Kumpati S. Narendra,et al.  Control of nonlinear dynamical systems using neural networks: controllability and stabilization , 1993, IEEE Trans. Neural Networks.

[10]  S. Gutman.  Uncertain dynamical systems--A Lyapunov min-max approach , 1979 .

[11]  Ovidiu Grigore,et al.  Robust nonlinear control using neural networks , 1995 .

[12]  Nader Sadegh,et al.  A perceptron network for functional identification and control of nonlinear systems , 1993, IEEE Trans. Neural Networks.

[13]  P. Ramadge,et al.  Discrete Time Stochastic Adaptive Control , 1981 .

[14]  C. Hollot.  Bound invariant Lyapunov functions: a means for enlarging the class of stabilizable uncertain systems , 1987 .

[15]  Ian R. Petersen,et al.  Structural Stabilization of Uncertain Systems: Necessity of the Matching Condition , 1985 .