Abstract
In this paper, an application of learning classifier systems is presented. An artificial multi-agent environment has been designed. Mate finding problem, a learning task inspired by nature, is considered which needs cooperation by two distinct agents to achieve the goal. The main feature of our system is existence of two parallel learning subsystems which have to agree on a common communication protocol to succeed in accomplishing the task. Apart from standard learning algorithms, a unification mechanism has been introduced to encourage coordinated behavior among the agents belonging to the same class. Experimental results are presented which demonstrate the effectiveness of this mechanism and the learning capabilities of classifier systems.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Booker, L. B., ‘Representing Attribute-based Concepts in a Classifier System’, Foundations of Genetic Algorithms, 1991.
Holland, J. H., ‘Properties of the Bucket Brigade’, Proceedings of the First International Conference on Genetic Algorithms and Their Applications, 1985.
Holland, J. H., ‘Escaping Brittleness: the possibilities of general-purpose learning algorithms applied to parallel rule-based systems’, Machine Learning: an Artificial Intelligence Approach, Vol. 2, 1986.
Goldberg, D. E., ‘Genetic Algorithms in Search, Optimization, and Machine Learning’, Addison Wesley, 1989.
Rahmani, A. T., Ono, N. (1992), ‘Genetic Evolution of Communication in Distributed Classifier Systems’, Proceedings of the 45th National Conference of Information Processing Society of Japan, 1992.
Riolo, R. L., ‘Bucket brigade performance: I. Long sequences of the classifier’, Proceedings of the Second ICGA, 1987.
Schuurmans, D., Scaeffer, J., ‘Representational Difficulties with Classifier Systems’, Proceedings of the Third ICGA, 1989.
Werner, G. M., Dyer M. G., ‘Evolution of Communication in Artificial Organisms’, Artificial Life II, Addison-Wesley, 1991.
Wilson, S. W., ‘Knowledge growth in an artificial animal’, Proceedings of the First ICGA, 1985.
Wilson, S. W., ‘Classifier systems and the ani-mat problem’, Machine Learning, 2, 1987.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag/Wien
About this paper
Cite this paper
Ono, N., Rahmani, A.T. (1993). Self-Organization of Communication in Distributed Learning Classifier Systems. In: Albrecht, R.F., Reeves, C.R., Steele, N.C. (eds) Artificial Neural Nets and Genetic Algorithms. Springer, Vienna. https://doi.org/10.1007/978-3-7091-7533-0_53
Download citation
DOI: https://doi.org/10.1007/978-3-7091-7533-0_53
Publisher Name: Springer, Vienna
Print ISBN: 978-3-211-82459-7
Online ISBN: 978-3-7091-7533-0
eBook Packages: Springer Book Archive