Abstract
This paper presents the emergence of the cooperative behavior for multiple robot agents by means of Genetic Programming (GP). For this purpose, we utilize several extended mechanisms of GP, i.e., (1) a co-evolutionary breeding strategy, (2) a controlling strategy of introns, which are non-executed code segments dependent upon the situation, and (3) a subroutine discovery technique. Our experimental domain is an escape problem. We have chosen the actual experimental settings so as to be close to a real world as much as possible. The validness of our approach is discussed with comparative experiments using other methods, i.e., Q-learning and Neural networks, which shows the superiority of GP-based multi-agent learning.
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
Hara, A., and Nagao, T., Emergence of Cooperative Behavior using ADG; Automatically Defined Groups, in Proc. of the Genetic and Evolutionary Computation Conference (GECCO99), Morgan Kaufmann, 1999
Haynes, T., Wainwright, R., and Sen, S., Evolving a Team, in Working Notes of the AAAI-95 Fall Symposium on Genetic Programming, AAAI Press, 1995
Hondo, N., Iba, H., Kakazu, Y., Sharing and Refinement for Reusable Subroutines of Genetic Programming, in Proc. 1996 IEEE International Conference on Evolutionary Computation (ICEC96), pp.565–570, 1996
Hondo, N., Iba, H., Kakazu, Y., Robust GP in Robot Learning, Parallel Problem Solving from Nature 4 (PPSN IV), Springer-Verlag, pp.751–760, 1996
Iba, H., Emergent Cooperation for Multiple Agents using Genetic Programming, in Parallel Problem Solving form Nature IV (PPSN96), 1996
Iba, H., Evolutionary Learning of Communicating Agents, Information Sciences, 108(1-4), 1998
Iba, H. and Terao, M., Controlling Effective Introns for Multi-Agent Learning by Genetic Programming, in Proc. of the Genetic and Evolutionary Computation Conference (GECCO2000), pp.419–426, 2000
Ito, T., Iba, H. and Kimura, M., Robot Programs Generated by Genetic Programming, Japan Advanced Institute of Science and Technology, IS-RR-96-0001I, in Genetic Programming 96, 1996
Koza, J., Genetic Programming II, Automatic Discovery of Reusable Subprograms, MIT Press, 1994
Luke, S. and Spector, L., Evolving Teamwork and Coordination with Genetic Programming, in Genetic Programming 96, MIT Press, 1996
Soule, T., Foster, J.A., and Dickinson, J., Code Growth in Genetic Programming, in Genetic Programming 96, 1996
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yanai, K., Iba, H. (2001). Multi-agent Robot Learning by Means of Genetic Programming: Solving an Escape Problem. In: Liu, Y., Tanaka, K., Iwata, M., Higuchi, T., Yasunaga, M. (eds) Evolvable Systems: From Biology to Hardware. ICES 2001. Lecture Notes in Computer Science, vol 2210. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45443-8_17
Download citation
DOI: https://doi.org/10.1007/3-540-45443-8_17
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42671-4
Online ISBN: 978-3-540-45443-4
eBook Packages: Springer Book Archive