Author :
Glorennec, Pierre Yves ; Jouffe, Lionel
Author_Institution :
Dept. d´´Inf., INSA de Rennes, France
Abstract :
This paper proposes an adaptation of Watkins´ Q-learning (1989, 1992) for fuzzy inference systems where both the actions and the Q-functions are inferred from fuzzy rules. This approach is compared with genetic algorithm on the cart-centering problem, showing its effectiveness
Keywords :
fuzzy control; fuzzy set theory; inference mechanisms; learning (artificial intelligence); Q-functions; cart-centering problem; fuzzy Q-learning; fuzzy inference systems; genetic algorithm; Equations; Fuzzy control; Fuzzy systems; Genetic algorithms; Learning; Neural networks; Process control; State estimation; State-space methods; Table lookup;
Conference_Titel :
Fuzzy Systems, 1997., Proceedings of the Sixth IEEE International Conference on
Conference_Location :
Barcelona
Print_ISBN :
0-7803-3796-4
DOI :
10.1109/FUZZY.1997.622790
