Title :
Adaptive reinforcement learning system for linearization control
Author :
Hwang, Kao-Shing ; Chao, Horng-Jen
Author_Institution :
Dept. of Electr. Eng., Nat. Chung Cheng Univ., Tainan, Taiwan
fDate :
10/1/2000 12:00:00 AM
Abstract :
A linearization scheme is proposed to demonstrate how a neural network scheme learns to linearize a system without any identification. The process occurs within an evaluator and a controller, which communicate with each other through reinforcement signals. From simulation results, the proposed learning scheme notably surpasses the conventional neural network approaches
Keywords :
backpropagation; control system analysis computing; linearisation techniques; neural nets; adaptive reinforcement learning system; backpropagation; control system linearisation; controller; evaluator; linearization control; neural network; nonlinear system analysis; reinforcement signals; Adaptive control; Adaptive systems; Artificial neural networks; Control systems; Learning; Neural networks; Nonlinear control systems; Nonlinear dynamical systems; Programmable control; Quantization;
Journal_Title :
Industrial Electronics, IEEE Transactions on
