Abstract
In Multi-Agent learning, agents must learn to select actions that maximize their utility given the action choices of the other agents. Cooperative Coevolution offers a way to evolve multiple elements that together form a whole, by using a separate population for each element. We apply this setup to the problem of multi-agent learning, arriving at an evolutionary multi-agent system (EA-MAS). We study a problem that requires agents to select their actions in parallel, and investigate the problem solving capacity of the EA-MAS for a wide range of settings.
Secondly, we investigate the transfer of the COllective INtelligence(COIN) framework to the EA-MAS. COIN is a proved engineering approach for learning of cooperative tasks in MASs, and consists of re-engineering the utilities of the agents so as to contribute to the global utility. It is found that, as in the Reinforcement Learning case, the use of the Wonderful Life Utility specified by COIN also leads to improved results for the EA-MAS.
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
De Jong, E.D., Pollack, J.B.: Ideal evaluation from coevolution. Evolutionary Computation 12(2) (2004)
Grenager, T., Powers, R., Shoham, Y.: Dispersion games: general definitions and some specific learning results. In: AAAI 2002 (2002)
Guestrin, C., Koller, D., Gearhart, C., Kanodia, N.: Generalizing plans to new environments in relational MDPs. In: International Joint Conference on Artificial Intelligence, IJCAI 2003 (2003)
Hardin, G.: The tragedy of the commons. Science 162, 1243–1248 (1968)
Kisiel-Dorohinicki, M., Socha, K.: Crowding Factor in Evolutionary Multi-Agent System For Multiobjective Optimization. In: Arabnia, H.R. (ed.) Proceedings of IC-AI 2001 – International Conference on Artificial Inteligence, June 2001, vol. 1, CSREA Press (2001)
Kok, J., Vlassis, N.: Sparse cooperative Q-learning. In: International Conference of Machine Learning (2004)
Miu, H.S., Leung, K.S., Leung, Y.: An evolutionary multi-agent system for object recognition in satellite images. In: The 2003 Congress on Evolutionary Computation, CEC 2003, pp. 520–527 (2003)
Nowé, A., Verbeeck, K.: Distributed Reinforcement Learning, loadbased routing a case study. In: Notes of the Neural, Symbolic and Reinforcement Methods for sequence Learning Workshop at IJCAI (1999)
Potter, M.A., De Jong, K.A.: Cooperative coevolution: An architecture for evolving coadapted subcomponents. Evolutionary Computation 8(1), 1–29 (2000)
’t Hoen, P., Bohte, S.: COllective INtelligence with sequences of actions. In: Lavrač, N., Gamberger, D., Todorovski, L., Blockeel, H. (eds.) ECML 2003. LNCS (LNAI), vol. 2837, pp. 181–192. Springer, Heidelberg (2003)
Hoen, P., Bohte, S.: COllective INtelligence with task assignment. In: Proceedings of CDOCS 2003, fortcoming. Also available as TR. LNCS (LNAI), Springer, Heidelberg (2003)
Tumer, K., Wolpert, D.: COllective INtelligence and Braess’ paradox. In: Proceedings of the Sixteenth National Conference on Artificial Intelligence, Austin, August 2000, pp. 104–109 (2000)
Urquhart, N., Ross, P., Paechter, B., Chisholm, K.: Solving a real world routing problem using multiple evolutionary agents. In: Guervós, J.J.M., Adamidis, P.A., Beyer, H.-G., Fernández-Villacañas, J.-L., Schwefel, H.-P. (eds.) PPSN 2002. LNCS, vol. 2439, pp. 871–882. Springer, Heidelberg (2002)
Weiss, G. (ed.): Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence. The MIT Press, Cambridge (1999)
Wolpert, D., Tumer, K.: Optimal payoff functions for members of collectives. Advances in Complex Systems 4(2/3), 265–279 (2001)
Wolpert, D.H., Tumer, K., Frank, J.: Using collective intelligence to route internet traffic. In: Advances in Neural Information Processing Systems-11, Denver, pp. 952–958 (1998)
Wolpert, D.H., Wheeler, K.R., Tumer, K.: General principles of learning-based multi-agent systems. In: Etzioni, O., Müller, J.P., Bradshaw, J.M. (eds.) Proceedings of the Third Annual Conference on Autonomous Agents (AGENTS 1999), May 1–5, pp. 77–83. ACM Press, New York (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
’t Hoen, P.J., de Jong, E.D. (2004). Evolutionary Multi-agent Systems. In: Yao, X., et al. Parallel Problem Solving from Nature - PPSN VIII. PPSN 2004. Lecture Notes in Computer Science, vol 3242. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30217-9_88
Download citation
DOI: https://doi.org/10.1007/978-3-540-30217-9_88
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23092-2
Online ISBN: 978-3-540-30217-9
eBook Packages: Springer Book Archive