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 a pursuit-evasion differential game in which both the pursuer and the evader self-learn their control strategies. The proposed technique is compared with the classical control strategy, Q(λ)-learning only, and the technique proposed in [1] in which a neural network is used as a function approximation for Q-learning. Computer simulations show the usefulness of the proposed technique.

Additional Metadata
Keywords Differential game, Function approximation, Fuzzy control, Multi-robot, Pursuit-evasion, Q(λ)-learning, Reinforcement learning
Persistent URL dx.doi.org/10.1109/ICSMC.2010.5641791
Conference 2010 IEEE International Conference on Systems, Man and Cybernetics, SMC 2010
Citation
Desouky, S.F. (Sameh F.), & Schwartz, H.M. (2010). Q(λ)-learning fuzzy logic controller for a multi-robot system. In Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics (pp. 4075–4080). doi:10.1109/ICSMC.2010.5641791