Unsupervised training of Multiobjective Agent Communication using Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.4340

  author =       "Kenneth J. Mackin and Eiichiro Tazaki",
  title =        "Unsupervised training of {M}ultiobjective {A}gent
                 {C}ommunication using {G}enetic {P}rogramming",
  booktitle =    "Proceedings of the Fourth International Conference on
                 Knowledge-Based Intelligent Engineering Systems and
                 Allied Technology",
  volume =       "2",
  pages =        "738--741",
  address =      "Brighton, UK",
  year =         "2000",
  month =        "30 " # aug # "-1 " # sep,
  publisher =    "IEEE",
  keywords =     "genetic algorithms, genetic programming, agent
                 communication protocols, agent group behaviour,
                 automatically defined function genetic programming,
                 multiagent systems, multiobjective agent communication,
                 multiobjective genetic programming, software agents,
                 software simulation, unsupervised learning, multi-agent
                 systems, unsupervised learning",
  URL =          "http://www.lania.mx/~ccoello/EMOO/mackin00.pdf.gz",
  DOI =          "doi:10.1109/KES.2000.884152",
  size =         "4 pages",
  abstract =     "Multiagent systems, in which independent software
                 agents interact with each other to achieve common
                 goals, complete distributed tasks concurrently under
                 autonomous control. Agent communication has been shown
                 to be an important factor in coordinating efficient
                 group behavior in agents. Most research on training or
                 evolving group behavior in multiagent systems used
                 predefined agent communication protocols. Designing
                 agent communication becomes a complex problem in
                 dynamic and large-scale systems. The problem is further
                 complicated in a multiobjective scenario. In order to
                 solve this problem, in our previous research we had
                 proposed a method applying genetic programming
                 techniques, in particular automatically defined
                 function genetic programming (ADF-GP), to allow agents
                 to autonomously learn effective agent communication
                 messaging. For this research we take this approach
                 further and combine multiobjective genetic programming
                 in order to adapt the system to a multiobjective
                 environment. In the proposed method separate agent
                 communication protocols are trained for each objective.
                 A software simulation of a multiagent transaction
                 system is used to observe the effectiveness of the
                 proposed method in multiobjective environments",

Genetic Programming entries for Kenneth J Mackin Eiichiro Tazaki