Evolutionary organizational search

ABSTRACT

In this paper, we proposed Evolutionary Organizational Search (EOS), an optimization method for the organizational control of multi-agent systems (MASs) based on genetic programming (GP). EOS adds to the existing armory a metaheuristic extension, which is capable of efficient search and less vulnerable to stalling at local optima than greedy methods due to its stochastic nature. EOS employs a flexible genotype which can be applied to a wide range of tree-shaped organizational forms. EOS also considers special constraints of MASs. A novel mutation operator, the redistribution operator, was proposed. Experiments optimizing an information retrieval system illustrated the adaptation of solutions generated by EOS to environmental changes.

REFERENCES

• 1: Virginia Dignum , Javier Vazquez-Salceda , Frank Dignum, A Model of Almost Everything: Norms, Structure and Ontologies in Agent Organizations, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, p.1498-1499, July 19-23, 2004, New York, New York [doi>10.1109/AAMAS.2004.20]
• 2: Bryan Horling , Victor Lesser, Quantitative organizational modeling and design for multi-agent systems, University of Massachusetts Amherst, 2006
• 3: Bryan Horling , Victor Lesser, A survey of multi-agent organizational paradigms, The Knowledge Engineering Review, v.19 n.4, p.281-316, December 2004 [doi>10.1017/S0269888905000317]
• 4: David J. Montana, Strongly typed genetic programming, Evolutionary Computation, v.3 n.2, p.199-230, Summer 1995 [doi>10.1162/evco.1995.3.2.199]
• 5: Sims, M., Corkill, D. and Lesser, V. Knowledgeable Automated Organization Design for Multi-Agent Systems. Technical Report 07--43, University of Massachusetts, Amherst, MA, 2007.
• 6: Young-pa So , Edmund H. Durfee, Designing organizations for computational agents, Simulating organizations: computational models of institutions and groups, MIT Press, Cambridge, MA, 1998

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
        I.2.11 Distributed Artificial Intelligence
            Subjects: Multiagent systems

Additional Classification:
  G. Mathematics of Computing
  G.2 DISCRETE MATHEMATICS
      G.2.1 Combinatorics
          Subjects: Combinatorial algorithms

General Terms:
Algorithms, Design, Performance

Keywords:
biologically-inspired approaches, experimental, genetic programming, multi-agent systems, organizational planning, systems