Title :
Fuzzy Q-learning and dynamical fuzzy Q-learning
Author :
Glorennec, Pierre Yves
Author_Institution :
Dept. of Inf., Inst. Nat. des Sci. Appliques, Rennes, France
Abstract :
This paper proposes two reinforcement-based learning algorithms: 1) fuzzy Q-learning in an adaptation of Watkins´ Q-learning for fuzzy inference systems; and 2) dynamical fuzzy Q-learning which eliminates some drawbacks of both Q-learning and fuzzy Q-learning. These algorithms are used to improve the rule base of a fuzzy controller
Keywords :
fuzzy control; fuzzy set theory; inference mechanisms; learning (artificial intelligence); uncertainty handling; dynamical fuzzy Q-learning; fuzzy Q-learning; fuzzy controller; fuzzy inference; reinforcement-based learning algorithms; rule base; Delay; Education; Feedback; Fuzzy control; Fuzzy systems; Inference algorithms; Learning; Process control; State estimation; State-space methods;
Conference_Titel :
Fuzzy Systems, 1994. IEEE World Congress on Computational Intelligence., Proceedings of the Third IEEE Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1896-X
DOI :
10.1109/FUZZY.1994.343739
