Skip to main content
Springer Nature Link
Log in

An Acceleration Method for Evolutionary Systems Based on Iterated Prisoner’s Dilemma

  • Conference paper
Reconfigurable Computing: Architectures, Tools and Applications (ARC 2007)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 4419))

Included in the following conference series:

Abstract

In this paper, we describe an acceleration method for evolutionary systems based on Iterated Prisoner’s Dilemma (IPD). In the systems, agents play IPD games with other agents, and strategies which earn more payoffs will gradually increase their ratio in the total population. Most computation time of the systems is occupied by IPD games, which are repeatedly played among the agents. In our method, repetition of moves in IPD games are detected, and payoffs by those moves are calculated at once by multipliers. In order to maximize the number of units for IPD games on one FPGA, multipliers are shared by the agents. We have implemented a system with the method on XC2VP100, and the speedup by the method is about four times compared with a system without the method.

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. Poundstone, W.: Prisoner’s Dilemma. Doubleday, New York (1992)

    Google Scholar 

  2. Lindgren, K.: Evolutionary Phenomena in Simple Dynamics. In: Artificial Life II, pp. 295–312 (1991)

    Google Scholar 

  3. Lindgren, K., Nordah, M.G.: Cooperation and Community Structure in Artificial Ecosystems. In: Artificial Life I, pp. 15–37 (1994)

    Google Scholar 

  4. Yamaguchi, Y., Maruyama, T., Hoshino, T.: High Speed Hardware Computation of Co-evolution Models. In: 5th European Conference on Artificial Life, pp. 566–574 (1999)

    Google Scholar 

  5. Yamaguchi, Y., et al.: A Co-processor System with a Virtex FPGA for Evolutionary Computation. In: Grünbacher, H., Hartenstein, R.W. (eds.) FPL 2000. LNCS, vol. 1896, pp. 240–249. Springer, Heidelberg (2000)

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Systems and Information Engineerings, University of Tsukuba, 1-1-1 Ten-ou-dai Tsukuba Ibaraki 305-8573, Japan

    Yoshiki Yamaguchi, Kenji Kanazawa, Yoshiharu Ohke & Tsutomu Maruyama

Authors
  1. Yoshiki Yamaguchi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kenji Kanazawa
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yoshiharu Ohke
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Tsutomu Maruyama
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Pedro C. Diniz Eduardo Marques Koen Bertels Marcio Merino Fernandes João M. P. Cardoso

Rights and permissions

Reprints and permissions

Copyright information

© 2007 Springer Berlin Heidelberg

About this paper

Cite this paper

Yamaguchi, Y., Kanazawa, K., Ohke, Y., Maruyama, T. (2007). An Acceleration Method for Evolutionary Systems Based on Iterated Prisoner’s Dilemma. In: Diniz, P.C., Marques, E., Bertels, K., Fernandes, M.M., Cardoso, J.M.P. (eds) Reconfigurable Computing: Architectures, Tools and Applications. ARC 2007. Lecture Notes in Computer Science, vol 4419. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-71431-6_34

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-71431-6_34

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-71430-9

  • Online ISBN: 978-3-540-71431-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics