Abstract
Learning can increase the flexibility and adaptability of the agents in a multiagent system. In this paper, we propose an automated system for solving classification and regression problems with the use of neural networks, where agents have three different learning algorithms and try to estimate a good network topology. We establish a competitive behavior between the types of agents, and we address a way in which agents can optimize the utility received for problem solving. Thus, the agents use neural networks to solve “external” problems given by the user, but they can also build their own “internal” problems out of their experience in order to increase their performance. The resulting behavior is an emergent property of the multiagent system.
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
Bellifemine, F.L., Caire, G., Greenwood, D.: Developing Multi-Agent Systems with JADE. Wiley Series in Agent Technology (2007)
Brown, G.W.: Iterative solutions of games by fictitious play. In: Koopmans, T.C. (ed.) Activitiy Analysis of Production and Allocation. ch. XXIV, pp. 374–376. Wiley, Chichester (1951)
Conitzer, V., Sandholm, T.: AWESOME: A general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents. In: Proceedings of the 20th International Conference on Machine Learning, ICML 2003, Washington, US, pp. 83–90 (2003)
Crites, R., Barto, A.G.: Elevator Group Control Using Multiple Reinforcement Learning Agents. Machine Learning 33, 235–262 (1998)
Curteanu, S., Leon, F.: Hybrid Neural Network Models Applied to a Free Radical Polymerization Process. In: Polymer-Plastics Technology and Engineering, vol. 45, pp. 1013–1023. Marcel Dekker, USA (2006)
Fahlman, S.E.: Faster Learning Variations on BackPropagation: An Empirical Study. In: Proceedings of the 1988 Connectionist Models Summer School, Morgan Kaufmann, Los Altos (1988)
Fisher, R.A.: The use of multiple measurements in taxonomic problems. Annual Eugenics, Part II 7, 179–188 (1936)
Grothmann R.: Multi-Agent Market Modeling based on Neural Networks. PhD Thesis, Faculty of Economics. University of Bremen, Germany (2002)
Herrero, A., Corchado, E., Pellicer, M.A., Abraham, A.: Hybrid Multi Agent-Neural Network Intrusion Detection with Mobile Visualization. Collection of Innovations in Hybrid Intelligent Systems, 320–328 (2008)
Hu, J., Wellman, M.P.: Multiagent reinforcement learning: Theoretical framework and an algorithm. In: Proceedings of the 15th International Conference on Machine Learning, ICML 1998, Madison, US, pp. 242–250 (1998)
Kudrycki, T. P.: Neural Network Implementation of a Medical Diagnostic Expert System. Master’s Thesis, College of Engineering. University of Cincinnati, USA (1988)
Leon, F., Leca, A.D., Atanasiu, G.M.: Strategy Management in a Multiagent System Using Neural Networks for Inductive and Experience-based Learning. In: Bratianu, C., Pop, N.A. (eds.) Management & Marketing, Challenges for Knowledge Society, vol. 5(4), pp. 3–28 (2010)
Leon, F., Piuleac, C.G., Curteanu, S.: Stacked Neural Network Modeling Applied to the Synthesis of Polyacrylamide Based Multicomponent Hydrogels. In: Macromolecular Reaction Engineering, vol. 4, pp. 591–598. WILEY-VCH Verlag GmbH & Co., Germany (2010)
Leon, F., Zaharia, M.H.: Stacked Heterogeneous Neural Networks for Time Series Forecasting. Mathematical Problems in Engineering 2010, Article ID 373648, 20 (2010)
Leon, F., Zaharia, M.H., Gâlea, D.: Performance Analysis of Categorization Algorithms. In: Proceedings of the 8th International Symposium on Automatic Control and Computer Science, Iaşi, Romania (2004)
Oeda, S., Ichimura, T., Yoshida, K.: Immune Multi Agent Neural Network and Its Application to the Coronary Heart Disease Database. In: Gelbukh, A. (ed.) CICLing 2001. LNCS, vol. 2004, pp. 1097–1105. Springer, Heidelberg (2001)
Quinlan, J.R.: Induction of Decision Trees. Machine Learning 1, 81–106 (1986)
Red’ko, V.G., Mosalov, O.P., Prokhorov, D.V.: A model of Baldwin effect in populations of self-learning agents. In: Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005, Montreal, Canada, pp. 1355–1360 (2005)
Riedmiller, M., Braun, H.: A direct adaptive method for faster backpropagation learning: The RPROP algorithm. In: IEEE Int. Conf. Neur. Net., vol. 1, pp. 586–591 (1993)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Rumelhart, D.E., McClelland, J.L. (eds.) Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1, pp. 318–362. The MIT Press, Cambridge (1986)
Shepard, R.N., Hovland, C.I., Jenkins, H.M.: Learning and memorization of classifications. Psychological Monographs 75 (1961)
Thrun, S. B., et al.: The MONK’s Problems - A Performance Comparison of Different Learning Algorithms. Technical Report CS-CMU-91-197, Carnegie Mellon University (1991)
Veit, D., Czernohous, C.: Automated Bidding Strategy Adaption using Learning Agents in Many-to-Many e-Markets. In: Proceedings of the Workshop on Agent Mediated Electronic Commerce V, AMEC-V, Melbourne, Australia (2003)
Watkins, C.J.C.H.: Learning from Delayed Rewards, PhD Thesis, King’s College, Cambridge University (1989)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Leon, F., Leca, A.D. (2011). Dual Manner of Using Neural Networks in a Multiagent System to Solve Inductive Learning Problems and to Learn from Experience. In: Brazier, F.M.T., Nieuwenhuis, K., Pavlin, G., Warnier, M., Badica, C. (eds) Intelligent Distributed Computing V. Studies in Computational Intelligence, vol 382. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24013-3_9
Download citation
DOI: https://doi.org/10.1007/978-3-642-24013-3_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24012-6
Online ISBN: 978-3-642-24013-3
eBook Packages: EngineeringEngineering (R0)