Fuzzy Q-learning and dynamical fuzzy Q-learning
Pierre Yves Glorennec · 1994
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.>