Abstract
This paper presents Mutant, a learning system for autonomous agents. Mutant is an adaptive control architecture founded on genetic techniques and reinforcement learning. The system allows an agent to learn some complex tasks without requiring its designer to fully specify how they should be carried out. An agent behavior is defined by a set of rules, genetically encoded. The rules are evolved over time by a genetic algorithm to synthesize some new better rules according to their respective adaptive function, computed by progressive reinforcements. The system is validated through an experimentation in collective robotics.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
James E. Baker. Adaptive selection methods for genetic algorithms. In Proceedings of the 1 st International Conference on Genetic Algorithms, pages 101–111, Pittsburgh, USA, 1985. Lawrence Erlbaum Associates.
Rodney A. Brooks. Integrated systems based on behaviors. SIGART, July 1991. Special issue on Integrated Intelligent Systems.
Rodney A. Brooks. Intelligence without reason. In Proceedings of the 12th International Joint Conference on Artificial Intelligence (IJCAI-91), pages 569–595, Sydney, Australia, August 1991. Morgan Kaufmann Publishers.
John H. Holland. Adaptation in Natural and Artificial Systems. MIT Press, Cambridge, MA, USA, 2nd edition, 1992.
Leslie P. Kaelbling, editor. Recent Advances in Reinforcement Learning. Kluwer Acadcemic Publishers, 1996. Reprinted from Machine Learning, 22(1,2,3), January, February, March 1996.
John R. Koza. Hierarchical genetic algorithms operating on population of computer programs. In Proceedings of the 11th International Joint Conference on Artificial Intelligence (IJCAI-89), San Mateo, 1989. Morgan Kaufmann Publishers.
Maja J. Mataric. Reinforcement learning in the multi-robot domain. Autonomous Robots, 4(1):73–83, March 1997.
Maja J. Mataric. Using communication to reduce locality in distributed multi-agent learning. Journal of Experimental and Theoretical Artificial Intelligence, 10(3):357–369, 1998. special issue on Learning in DAI Systems, Gerhard Weiß, ed.
S. D. Whitehead and D. H. Ballard. Active perception and reinforcement learning. Neural Computation, 2(4):409–419, 1991.
C. Watkins and P. Dayan. Technical note: Q-Learning. Machine Learning, 1992.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Calderoni, S., Marcenac, P. (1999). Mutant: A Genetic Learning System. In: Foo, N. (eds) Advanced Topics in Artificial Intelligence. AI 1999. Lecture Notes in Computer Science(), vol 1747. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46695-9_18
Download citation
DOI: https://doi.org/10.1007/3-540-46695-9_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66822-0
Online ISBN: 978-3-540-46695-6
eBook Packages: Springer Book Archive