Abstract
The fuzzy min-max neural network constitutes a neural architecture that is based on hyperbox fuzzy sets and can be incrementally trained by appropriately adjusting the number of hyperboxes and their corresponding volumes. Two versions have been proposed: for supervised and unsupervised learning. In this paper a modified approach is presented that is appropriate for reinforcement learning problems with discrete action space and is applied to the difficult task of autonomous vehicle navigation when no a priori knowledge of the enivronment is available. Experimental results indicate that the proposed reinforcement learning network exhibits superior learning behavior compared to conventional reinforcement schemes.
Similar content being viewed by others
References
P.K. Simpson, “Fuzzy min-max neural networks — Part 1: classification”, IEEE Trans. on Neural Networks, Vol. 3, No. 5, pp. 776–786, 1992.
P.K. Simpson, “Fuzzy min-max neural networks — Part 2: clustering”, IEEE Trans. on Fuzzy Systems, Vol. 1, No. 1, pp. 32–45, 1993.
A. Likas, K. Blekas and A. Stafylopatis, “Application of the fuzzy min-max neural network classifier to problems with continuous and discrete attributes”, in Proc. IEEE Workshop on Neural Networks for Signal Processing, pp. 163–170, Ermioni, Greece, 1994.
D. Kontoravdis and A. Stafylopatis, “Reinforcement learning techniques for autonomous vehicle control”, Neural Network World, Vols. 3–4, pp. 329–346, 1992.
L. Lin, “Self-improving reactive agents based on reinforcement learning, planning and teaching”, Machine Learning, Vol. 8, pp. 293–321, 1992.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Likas, A., Blekas, K. A reinforcement learning approach based on the fuzzy min-max neural network. Neural Process Lett 4, 167–172 (1996). https://doi.org/10.1007/BF00426025
Issue Date:
DOI: https://doi.org/10.1007/BF00426025