Co-operative Reinforcement Learning by payoff filters (Extended abstract)

  • Sadayoshi Mikami
  • Yukinori Kakazu
  • Terence C. Fogarty
Extended Abstracts
Part of the Lecture Notes in Computer Science book series (LNCS, volume 912)


This paper proposes an extension of Reinforcement Learning (RL) to acquire co-operation among agents. The idea is to learn filtered payoff that reflects a global objective function but does not require mass communication among agents. It is shown that the acquisition of two typical co-operation tasks is realised by preparing simple filter functions: an averaging filter for co-operative tasks and an enhancement filter for deadlock prevention tasks. The performance of these systems was tested through computer simulations of n-persons prisoner's dilemma, and a traffic control problem.


  1. 1.
    Sutton, R.S., ed.: Reinforcement Learning, Kluer Academic (1993)Google Scholar
  2. 2.
    Connell, J.H., Mahadevan, S.: Robot Learning, Kluer Academic (1993)Google Scholar
  3. 3.
    Steels. L.: Co-operation between Distributed Agents through Self-Organisation, Decentralised AI, North-Holland (1990)Google Scholar
  4. 4.
    Arkin, R.C.: Integration of Reactive and Telerobotic Control in Multi-agent Robotic System, From Animals to Animats 3, MIT Press (1994) 473 478Google Scholar
  5. 5.
    Mataric, M.J.: Learning to Behave Socially, From Animals to Animats 3, MIT Press (1994)453 462Google Scholar
  6. 6.
    Tan, M.: Multi-Agent Reinforcement Learning, Proc. Machine Learning (1993) 330 337Google Scholar
  7. 7.
    Fogel, D.B.: Evolving Behaviors in the Iterated Prisoner's Dilemma, Evolutionary Computation, 1 1 (1993)Google Scholar
  8. 8.
    Mikami, S., Kakazu, Y.: Genetic Reinforcement Learning for Co-operative Traffic Signal Control, IEEE World Congress on Computational Intelligence (1994) 223 228Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Sadayoshi Mikami
    • 1
    • 2
  • Yukinori Kakazu
    • 1
  • Terence C. Fogarty
    • 2
  1. 1.Hokkaido UniversitySapporoJapan
  2. 2.University of the West of EnglandFrenchayUK

Personalised recommendations