Agent-Based Simulation of Learning Social Norms in Traffic Signal Systems

  • Kokolo Ikeda
  • Ikuo Morisugi
  • Hajime Kita
Conference paper
Part of the Springer Series on Agent Based Social Systems book series (ABSS, volume 6)


Formation and maintenance of social norms are important to keep multi-agent systems. Though the mechanisms how such norms are formed and maintained or collapsed are not clear, agent-based simulation is a promising approach for analysis. In this paper a compact framework of simulation, with learning agents in traffic signal system, is presented. Through some preliminary experiments, for example to analyze how the traffic volume effects the norm formation, the potential of the framework is shown.


Genetic Algorithm Norm Formation Typical Trial Payoff Matrix Left Graph 
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.


  1. [Axelrod 1986]
    Axelrod, R.: “An Evolutionary Approach to Norms,” The American Political Science Review, Vol. 80, No. 4, pp. 1095–1111, 1986.CrossRefGoogle Scholar
  2. [Durkheim 1985]
    Durkheim, E.: “Le suicide: etude de sociologie,” Presses universitaires de France, 1985.Google Scholar
  3. [Eshelman and Schaffer 1993]
    Eshelman, L. and Schaffer, J.: “Real-coded genetic algorithms and interval schemata,” Foundations of Genetic Algorithms, Vol. 2, pp. 187–202, 1993.Google Scholar
  4. [Hobbes 2004]
    Hobbes, T.: “The Leviathan,” KESSINGER PUB CO, 2004.Google Scholar
  5. [Rosenstein and Barto, 2001]
    Rosenstein, M.T. and Barto, A.G.: “Robot weightlifting by direct policy search,” Proceedings of the 17th International Joint Conference on Artificial Intelligence, vol. 2, pp. 839–844, 2001.Google Scholar
  6. [Shibata, et. al 2003]
    Shibata, K., Ueda, M. and Ito, K.: “Emergence and Differentiation Model of Individuality and Socility by Reinforcement Learning,” The Society of Instrument and Control Engineers, Vol. 39, No. 5, 2003Google Scholar
  7. [Shoham and Tenneholtz 1993]
    Shoham, Y. and Tennenholtz, M.: “Co-learning and the evolution of social activity,” Technical Report STAN-CS-TR-94-1511, 1993Google Scholar
  8. [Shoham and Tenneholtz 1997]
    Shoham, Y. and Tennenholtz, M.: “On the Emergence of Social Conventions: Modeling, Analysis, and Simulations,” Artificial Intelligence, Vol. 94, No. 1–2, pp. 139–166, 1997CrossRefGoogle Scholar

Copyright information

© Springer 2009

Authors and Affiliations

  • Kokolo Ikeda
    • 1
  • Ikuo Morisugi
    • 2
  • Hajime Kita
    • 1
  1. 1.Kyoto UniversityKyotoJAPAN
  2. 2.NTT WEST CorporationOsakaJAPAN

Personalised recommendations