Abstract
A reinforcemen-based fuzzy neural network control with automatic rule generation (RBFNNC) is proposed. A set of optimized fuzzy control rules can be automatically generated through reinforcement learning based on the state variables of object system. RBFNNC was applied to a cart-pole balancing system and simulation result shows significant improvements on the rule generation.
Similar content being viewed by others
References
Patrikar A., Provence J., Control of dynamic system using fuzzy logic and neural networks, International Journal of Intelligent Systems, 1993, 8: 727–748
Kosko B., Neural Network and Fuzzy Systems, Prentice-Hall, Englewood Cliffs. NJ, 1991: 225–228, 304–306, 327–335
Berenji H.R., Khedkar P., Learning and tuning fuzzy logic controllers throug reinforcements, IEEE Transactions on Neural Networks, 1992, 3(5): 724–740
Nauck D., Kruse R., NEFCON-I: An X-window based simulator for neural fuzzy controllers, Proc. IEEE Int. Conf. Neural Networks, IEEE World Congress on Computational Intelligence (WCCVI ’94), Orlanda, Jun. 26–Jul. 2,1994
Nauck U. D., Kruse R., A fuzzy neural network learning fuzzy control rules and membership functions by fuzzy error backpropagation, Proc. IEEE Int. Conf. Neural Networks (ICNN’93), San Francisco, Mar. 28–Apr.l, 1993: 1022–1027
Author information
Authors and Affiliations
Additional information
Project supported by the Science Foundation of Shanghai Municipal Commission of Education (980034)
About this article
Cite this article
Wu, Gf., Dong, Jq., Chen, Ym. et al. Reinforcement-based fuzzy neural network control with automatic rule generation. J. of Shanghai Univ. 3, 282–286 (1999). https://doi.org/10.1007/s11741-999-0005-8
Received:
Issue Date:
DOI: https://doi.org/10.1007/s11741-999-0005-8