This paper addresses the problem of tuning the input and the output parameters of a fuzzy logic controller. A novel technique that combines Q(λ)-learning with function approximation (fuzzy inference system) is proposed. The system learns autonomously without supervision or a priori training data. The proposed technique is applied to three different pursuit-evasion differential games. The proposed technique is compared with the classical control strategy, Q(λ)-learning only, and the technique proposed by Dai et al. (2005) in which a neural network is used as a function approximation for Q-learning. Computer simulations show the usefulness of the proposed technique. Copyright

differential game, function approximation, fuzzy control, pursuit-evasion, Q(λ)-learning, reinforcement learning
International Journal of Adaptive Control and Signal Processing
Department of Systems and Computer Engineering

Desouky, S.F. (Sameh F.), & Schwartz, H.M. (2011). Q(λ)-learning adaptive fuzzy logic controllers for pursuit-evasion differential games. International Journal of Adaptive Control and Signal Processing, 25(10), 910–927. doi:10.1002/acs.1249