Title :
CMAC-based adaptive critic self-learning control
Author :
Lin, Chun-shin ; Kim, Hyongsuk
Author_Institution :
Dept. of Electr. & Comput. Eng., Missouri Univ., Columbia, MO, USA
fDate :
9/1/1991 12:00:00 AM
Abstract :
A technique that integrates the cerebellar model articulation controller (CMAC) into a self-learning control scheme developed by A.G. Barto et al. (IEEE Trans. Syst. Man., Cybern., vol.SMC-13, p.834-46, Sept./Oct. 1983) is presented. Instead of reserving one input line (as a memory) for each quantized state, the integrated technique distributively stores learned information; this reduces the required memory and makes the self-learning control scheme applicable to problems of larger size. CMAC´s capability with regard to information interpolation also helps improve the learning speed
Keywords :
adaptive control; interpolation; learning systems; self-adjusting systems; CMAC; adaptive control; box based scheme; cerebellar model articulation controller; information interpolation; learning systems; self-learning control; Adaptive control; Control systems; Force control; Interpolation; Multi-layer neural network; Neural networks; Programmable control; Size control; State-space methods;
Journal_Title :
Neural Networks, IEEE Transactions on
