• DocumentCode
    3277101
  • Title

    Multi-Agent Coevolutionary Learning Method Based on Individual Rule Set

  • Author

    Xue Hongtao ; Shen Lincheng ; Zhu Huayong ; Zhang Daibing ; Xiang Xiaojia

  • Author_Institution
    Coll. of Mechatron. Eng. & Autom., Nat. Univ. of Defense Technol., Changsha, China
  • fYear
    2013
  • fDate
    16-18 Jan. 2013
  • Firstpage
    978
  • Lastpage
    981
  • Abstract
    The process of cooperative or competitive co evolutionary learning exist among multiple species in the ecological and artificial system, which is one of the primary features for emergent phenomena and behaviors. In this paper, we propose a multi-agent co evolutionary learning method based on the individual rule set, define the co evolutionary learning framework. We design a typical "predator-prey" competition system as an example, define the rule set and implement the system by multi-agent modeling language, Net Logo. With simulation experiments of the birds-bugs prey problem, we analyze emergent behaviors in the process of co evolutionary learning.
  • Keywords
    evolutionary computation; learning (artificial intelligence); multi-agent systems; simulation languages; NetLogo; artificial system; birds-bugs prey problem; competitive coevolutionary learning; cooperative coevolutionary learning; ecological system; individual rule set; multiagent coevolutionary learning method; multiagent modeling language; predator-prey competition system; Analytical models; Birds; Computer bugs; Learning systems; Predator prey systems; Sociology; Statistics; Coevolutionary Learning; Emergent Behavior; Multi-Agent System; NetLogo; Rule Set;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent System Design and Engineering Applications (ISDEA), 2013 Third International Conference on
  • Conference_Location
    Hong Kong
  • Print_ISBN
    978-1-4673-4893-5
  • Type

    conf

  • DOI
    10.1109/ISDEA.2012.233
  • Filename
    6456181