Abstract
We present two architectures, each designed to search 2-Dimensional mazes in order to locate a “goal” position, both of which perform on-line learning as the search proceeds. The first architecture is a form of Adaptive Heuristic Critic which uses a Genetic Algorithm to determine the Action Policy and a Radial Basis Function Neural Network to store the acquired knowledge of the Critic. The second is a stimulus-response Classifier System (CS) which uses a Genetic Algorithm, applied “Michigan” style, for rule generation and the “Bucket Brigade” algorithm for rule reinforcement. Experiments conducted using agents based upon each architectural model lead us to a comparison of performance, and some observations on the nature and relative levels of abstraction in the acquired knowledge.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Barto A. G., Sutton R. S., Watkins C. J. C. H., 1989, ‘Learning and Sequential Decision Making', COINS Technical Report 89–95
Booker L. B., 1982, ‘Intelligent Behaviour as an Adaptation to the Task Environment’ PhD dissertation, University of Michigan
Booker L. B., Goldberg D. E., Holland J. H., 1989, ‘Classifier Systems and Genetic Algorithms', Artificial Intelligence 40, pp.235–282
Goldberg, D. E., 1989, ‘Genetic Algorithms in Search, Optimization and Machine Learning', Addison Wesley
Lin L., PhD thesis, 1993, ‘Reinforcement Learning for Robots using Neural Networks', School of Comp. Science, Carnegie Mellon University Pittsburgh, USA
Parodi A., Bonelli P., 1993, ‘A New Approach to Fuzzy Classifier Systems', Proceedings of the 5th International Conference on Genetic Algorithms, pp.223–230
Pipe A. G. 1, Fogarty T. C., Winfield A., 1994, ‘A Hybrid Architecture for Learning Continuous Environmental Models in Maze Problems', to appear in Procs. of 3rd International Conference on Simulation of Adaptive Behaviour, Brighton
Pipe A. G. 2, Fogarty T. C., Winfield A., 1994, ‘Hybrid Adaptive Heuristic Architectures for Learning in Mazes with Continuous Search Spaces', to appear in Procs. of 3rd Parallel Problem Solving from Nature, Jerusalem
Poggio T., Girosi F., 1989, ‘A Theory of Networks for Approximation and Learning', MIT Cambridge, MA, AI lab. Memo 1140
Roberts G., 1989, ‘A rational reconstruction of Wilson's Animat and Holland's CS-1', Procs. of 3rd Int. Conf. on Genetic Algorithms, pp. 317–321, Ed. Schaffer J. D., Morgan Kaufmann
Roberts G., 1991, ‘Classifier Systems for Situated Autonomous Learning', PhD thesis, Edinburgh University
Roberts G., 1993, ‘Dynamic Planning for Classifier Systems', Proceedings of the 5th International Conference on Genetic Algorithms, pp.231–237
Sanner R. M., Slotine J. E., 1991, ‘Gaussian Networks for Direct Adaptive Control', Nonlinear Systems Lab., MIT, Cambridge, USA, Tech. Rep. NSL-910503
Sutton R. S., 1984, PhD thesis ‘Temporal Credit Assignment in Reinforcement Learning', University of Massachusetts, Dept. of computer and Info. Science
Sutton R. S., 1991, ‘Reinforcement Learning Architectures for Animats', From Animals to Animats, pp288–296, Editors Meyer, J., Wilson, S., MIT Press
Thrun S. B., 1992, ‘The Role of Exploration in Learning', Handbook of Intelligent Control: Neural, Fuzzy, & Adaptive Approaches, Van Nostrand Reinhold, Ed. White D., Sofge D.
Werbos P. J., 1992, ‘Approximate Dynamic Programming for Real-Time Control and Neural Modelling', Handbook of Intelligent Control: Neural, Fuzzy, and Adaptive Approaches, Van Nostrand Reinhold, Ed. White D., Sofge D.
Wilson S. W., 1985, ‘Knowledge growth in an artificial animal', Procs. of Int. Conf. on Genetic Algorithms and their Applications, pp. 16–23, Editor Grefenstette J. J.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pipe, A.G., Carse, B. (1994). A comparison between two architectures for searching and learning in maze problems. In: Fogarty, T.C. (eds) Evolutionary Computing. AISB EC 1994. Lecture Notes in Computer Science, vol 865. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-58483-8_18
Download citation
DOI: https://doi.org/10.1007/3-540-58483-8_18
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-58483-4
Online ISBN: 978-3-540-48999-3
eBook Packages: Springer Book Archive