Testing three paradigms for evolving groups of cooperative, simple agents (original) (raw)

Abstract

A comparison of methods for evolving groups of simple evolving agents is performed and analyzed. The symbot model is used as a testbed for comparing three possible representations of a population or group of populations used to evolve a cooperative simulated robot team. The goal of this work is to identify the effect of the different representations upon the total group effectiveness and individual contributions of group members.

Preview

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. D. Ashlock, J. Walker, and J. Oliver. The evolution of ultrasimple virtual robots. In N. Bourbakis, editor, Proceedings of 2nd IEEE Intl. Joint Symp. on Intelligence and Systems, Proceedings of 2nd IEEE IAR, pages 170–177. IEEE, 1996.
    Google Scholar
  2. V. Braitenberg. Vehicles, experiments in synthetic psychology. MIT Press, Cambridge, Mass., 1984.
    Google Scholar
  3. D. Cliff, I. Harvey, and P. Husbands. Explorations in evolutionary robotics. Adaptive Behavior, 2:73–110, 1993.
    Google Scholar
  4. D. Goldberg. Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley Publishing Company, Inc., Reading, MA, 1989.
    Google Scholar
  5. I. Harvey, P. Husbands, and D. Cliff. Issues in evolutionary robotics. In J.A. Meyer, H.L. Roitblat, and S. Wilson, editors, From Animals to Animats 2, Proc. of 2nd Intl. Conf. on Simulation of Adaptive Behavior, pages 364–373, Boston MA, 1993. MIT Press.
    Google Scholar
  6. B. Holdobler and E. O. Wilson. The Ants. Harvard Univ. Press, Boston, MA, 1990.
    Google Scholar
  7. M. Mataric. Designing and understanding adaptive group behavior. Adaptive Behavior, 4(1):51–80, 1995.
    Google Scholar
  8. L. Steels. Emergent functionality in robotic agents through on-line evolution. In C. Langton, editor, Artificial Life IV, volume 11 of Santa Fe Institute Studies in the Sciences of Complexity, pages 8–14, Reading, 1995. Addison-Wesley.
    Google Scholar
  9. J. Walker. Evolution of simple virtual robots using genetic algorithms. Master's thesis, Iowa State University, Ames, IA, 1995.
    Google Scholar

Download references

Author information

Authors and Affiliations

  1. Department of Mechanical Engineering and Iowa Center for Emerging Manufacturing Technology, Iowa State University, 50011, Ames, Iowa
    John F. Walker

Editor information

V. W. Porto N. Saravanan D. Waagen A. E. Eiben

Rights and permissions

© 1998 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Walker, J.F. (1998). Testing three paradigms for evolving groups of cooperative, simple agents. In: Porto, V.W., Saravanan, N., Waagen, D., Eiben, A.E. (eds) Evolutionary Programming VII. EP 1998. Lecture Notes in Computer Science, vol 1447. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0040760

Download citation

Keywords

These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Publish with us