Abstract
We present an improvement to evolutionary learning of cooperative behavior which incorporates some accountability measure for strategy components into the evolutionary learning process. Our evolutionary approach is based on evolving sets of prototypical situation-action pairs (strategies) that together, with the nearest-neighbor rule, represent the decision making of our agents. The basic idea of our improvement is to collect data for each pair showing the results of its applications. We then choose those pairs in the parent strategies that had positive results for the construction of new sets of pairs for our strategies.
Our experiments within the OLEMAS system show that the incorporation of accountability results in substantial improvements of both on- and off-line learning when compared to the basic evolutionary approach. In nearly all experiments, either the agent teams required less learning time or found better strategies. In many cases both were observed.
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
Benda, M., Jagannathan, V., Dodhiawalla, R.: An Optimal Cooperation of Knowledge Sources, Technical Report BCS-G201e-28, Boeing AI Center (1985)
Denzinger, J., Ennis, S.: Being the new guy in an experienced team – enhancing training on the job. In: Proc. AAMAS 2002, pp. 1246–1253. ACM Press, New York (2002)
Denzinger, J., Fuchs, M.: Experiments in Learning Prototypical Situations for Variants of the Pursuit Game. In: ICMAS 1996, pp. 48–55. AAAI Press, Menlo Park (1996)
Denzinger, J., Kordt, M.: Evolutionary On-line Learning of Cooperative Behavior with Situation-Action-Pairs. In: Proc. ICMAS 2000, pp. 103–110. IEEE Press, Los Alamitos (2000)
Haynes, T., Wainwright, R., Sen, S., Schoenefeld, D.: Strongly typed genetic programming in evolving cooperation strategies. In: Proc. 6th GA, pp. 271–278. Morgan Kaufmann, San Francisco (1995)
Hu, J., Wellman, M.P.: Multiagent reinforcement learning: theoretical framework and an algorithm. In: Proc. 15th Machine Learning, pp. 242–250. AAAI Press, Menlo Park (1998)
Lanzi, P.L.: Learning Classifier Systems from a Reinforcement Learning Perspective, Technical Report 00-03, Politecnico di Milano (2000)
Manela, M., Campbell, J.A.: Designing good pursuit problems as testbeds for distributed AI: a novel application of genetic algorithms. In: Proc. 5th MAAMAW, pp. 231–252 (1993)
Stone, P.: Layered Learning in Multi-Agent Systems: A Winning Approach to Robotic Soccer. MIT Press, Cambridge (2000)
Tan, M.: Multi-agent reinforcement learning: Independent vs cooperative agents. In: Proc. 10th Machine Learning, pp. 330–337. Morgan Kaufmann, San Francisco (1993)
Watkins, C.J.C.H.: Learning from Delayed Rewards, PhD thesis, University of Cambridge (1989)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Denzinger, J., Ennis, S. (2003). Improving Evolutionary Learning of Cooperative Behavior by Including Accountability of Strategy Components. In: Schillo, M., Klusch, M., Müller, J., Tianfield, H. (eds) Multiagent System Technologies. MATES 2003. Lecture Notes in Computer Science(), vol 2831. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-39869-1_18
Download citation
DOI: https://doi.org/10.1007/978-3-540-39869-1_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20124-3
Online ISBN: 978-3-540-39869-1
eBook Packages: Springer Book Archive