1994/01/01 by H.R. Berenji · 1 citation
Computer Science · Mathematics · #Reinforcement Learning in Robotics #Robotic Path Planning Algorithms #Adaptive Dynamic Programming Control #Fuzzy set operations #Fuzzy logic #Reinforcement learning #Artificial intelligence #Defuzzification #Fuzzy classification #Fuzzy number #Computer science #Type-2 fuzzy sets and systems #Neuro-fuzzy #Fuzzy set #Fuzzy control system #Mathematical optimization #Mathematics
paper · doi:10.1109/fuzzy.1994.343737
openalex publication_date 1994/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29
Fuzzy reinforcement learning (FRL) involves "jump starting" reinforcement learning with fuzzy logic rules. By using FRL, prior domain knowledge, which may be very approximate and imprecise, can be expressed in terms of fuzzy rules and refined later through the learning process. In this paper, we develop a new algorithm called fuzzy Q-learning (or FQ-Learning) which extends Watkin's Q-learning method. It can be used for decision processes in which the goals and/or the constraints, but not necessarily the system under control, are fuzzy in nature. An example of a fuzzy constraint is: "the weight of object A must not be substantially heavier than w" where w is a specified weight. Similarly, an example of a fuzzy goal is: "the robot must be in the vicinity of door k". We show that FQ-learning provides an alternative solution to this problem which is simpler than the Bellman-Zadeh's fuzzy dynamic programming approach. We apply the algorithm to a multistage decision making problem and a navigation task.>