Evolving team behaviors with specialization

  • Authors:
  • G. S. Nitschke;A. E. Eiben;M. C. Schut

  • Affiliations:
  • Ikegami Lab, Department of General Systems Studies, University of Tokyo, Tokyo, Japan;Computational Intelligence Group, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands;Computational Intelligence Group, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands

  • Venue:
  • Genetic Programming and Evolvable Machines
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

This article evaluates Collective Neuro-Evolution (CONE), a cooperative co-evolutionary method for solving collective behavior tasks and increasing task performance via facilitating behavioral specialization in agent teams. Specialization is used as a problem solving mechanism, and its emergence is guided and regulated by CONE. CONE is comparatively evaluated with related methods in a simulated evolutionary robotics pursuit-evasion task. This task required multiple pursuer robots to cooperatively capture evader robots. Results indicate that CONE is appropriate for evolving specialized behaviors. The interaction of specialized behaviors produces behavioral heterogeneity in teams and collective prey capture behaviors that yield significantly higher performances compared to related methods.