Skip to main content
Springer Nature Link
Log in

Analyzing and Taming Collective Learning of a Multiagent System with Connected Replicator Dynamics

  • Conference paper
  • First Online:
New Frontiers in Artificial Intelligence (JSAI 2003, JSAI 2004)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 3609))

  • 610 Accesses

Abstract

This paper analyzes complex collective behaviors of a multiagent system, which consists of interacting agents with evolutionary learning capabilities. The interaction and learning of the agents are modeled by the concept of Connected Replicator Dynamics expanded from evolutionary Game Theory.The dynamic learning system we analyze shows various behavioral and decision changes including bifurcation of chaos in the sense of physical sciences.The main contributions of the paper are summarized as follows: (1) In amultiagent system, the emergence of chaotic behaviors is general and essential, even if each agent does not have chaotic properties; and (2) However,asimple controlling agent with the Keep-It-Simple-Stupid (KISS) principle, or a sheep-dog agent, is able to domesticate or tame the complex behaviors.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Axelrod, R.: The Complexity of Cooperation. Princeton University Press, Princeton (1997)

    MATH  Google Scholar 

  2. Axtell, R.L.: Why Agents? On The Varied Motivations for Agent Computing in the Social Sciences. Working paper No.17, Center on Social and Economic Dynamics, The Brookings Inst. (2000), http://www.brook.edu/es/dynamics

  3. Hogg, T., Huberman, B.: Controlling Chaos in Distributed Systems. IEEE Transactions on Systems, Man, and Cybernetics 21(6), 1325–1332 (1991)

    Article  Google Scholar 

  4. Ushio, T., Imamori, T., Yamasagi, T.: Controlling Chaos in Discrete-Time Computational Ecosystem. In: Chen, G. (ed.) Controlling Chaos and Bifurcations in Engineering Systems, pp. 625–644. CRC Press, Boca Raton (2000)

    MATH  Google Scholar 

  5. Kunigami, M., Terano, T.: Connected Replicator Dynamics and Their Control in a Learning Multi-Agent System. In: Liu, J., Cheung, Y.-m., Yin, H. (eds.) IDEAL 2003. LNCS, vol. 2690, pp. 18–26. Springer, Heidelberg (2003)

    Google Scholar 

  6. Sato, Y., Crutchfield, J.P.: Coupled Replicator Equations for the Dynamics of Learning in Multiagent Systems, working paper of Santa Fe Institute (April 2002), http://www.santafe.edu/sfi/publications/Working-Papers/02-04-017_OnlinePDF.pdf

  7. Ott, E., Grebogi, C., Yorke, J.A.: Controlling Chaos. Physical Review Letters 64, 1196–1199 (1990)

    Article  MathSciNet  Google Scholar 

  8. Pyragas, K.: Continuous Control of Chaos by Self-Controlling Feedback. Physics Letters A 170(6), 421–428 (1992)

    Article  Google Scholar 

  9. Kittel, A., Parisi, J., Pyragas, K.: Delayed Feedback Control of Chaos by Self-Adapting Delay Time. Physics Letters A 198, 433–436 (1995)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Graduate School of Business Science, Tsukuba University, 3-29-1, Otsuka, Bunkyo-ku, Tokyo 112-0012, Japan

    Masaaki Kunigami & Takao Terano

  2. Computational Intelligence and Systems Science, Tokyo Institute of Technology, 4259 Nagatsuda-Cho, Midori-ku, Yokohama 226-8502, Japan

    Takao Terano

Authors
  1. Masaaki Kunigami
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Takao Terano
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Akito Sakurai Kôiti Hasida Katsumi Nitta

Rights and permissions

Reprints and permissions

Copyright information

© 2007 Springer Berlin Heidelberg

About this paper

Cite this paper

Kunigami, M., Terano, T. (2007). Analyzing and Taming Collective Learning of a Multiagent System with Connected Replicator Dynamics. In: Sakurai, A., Hasida, K., Nitta, K. (eds) New Frontiers in Artificial Intelligence. JSAI JSAI 2003 2004. Lecture Notes in Computer Science(), vol 3609. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-71009-7_11

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-71009-7_11

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-71008-0

  • Online ISBN: 978-3-540-71009-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics