论文信息 - Fuzzy Q-learning and dynamical fuzzy Q-learning

Fuzzy Q-learning and dynamical fuzzy Q-learning

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.<<ETX>>

P. Y. Glorennec | P. Glorennec | P.Y. Glorennec

[1] Hugues Bersini,et al. REINFORCEMENT LEARNING AND RECRUITMENT MECHANISM FOR ADAPTIVE DISTRIBUTED CONTROL , 1992 .

[2] Paul E. Utgoff,et al. A Teaching Method for Reinforcement Learning , 1992, ML.

[3] Ben J. A. Kröse,et al. Learning from delayed rewards , 1995, Robotics Auton. Syst..

[4] Andrew McCallum,et al. Using Transitional Proximity for Faster Reinforcement Learning , 1992, ML.

[5] Hamid R. Berenji,et al. Learning and tuning fuzzy logic controllers through reinforcements , 1992, IEEE Trans. Neural Networks.

[6] Long Ji Lin,et al. Self-improvement Based on Reinforcement Learning, Planning and Teaching , 1991, ML.

[7] Richard S. Sutton,et al. Sequential Decision Problems and Neural Networks , 1989, NIPS 1989.

[8] Richard S. Sutton,et al. Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[9] Steven D. Whitehead,et al. A Complexity Analysis of Cooperative Mechanisms in Reinforcement Learning , 1991, AAAI.

[10] P. Y. Glorennec. Neuro-fuzzy control using reinforcement learning , 1993, Proceedings of IEEE Systems Man and Cybernetics Conference - SMC.

[11] Kumpati S. Narendra,et al. Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.