Advertisement

A framework for coordination and learning among teams of agents

  • Hung H. Bui
  • Svetha Venkatesh
  • Dorota Kieronska
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1441)

Abstract

We present a framework for team coordination under incomplete information based on the theory of incomplete information games. When the true distribution of the uncertainty involved is not known in advance, we consider a repeated interaction scenario and show that the agents can learn to estimate this distribution and share their estimations with one another. Over time, as the set of agents' estimations become more accurate, the utility they can achieve approaches the optimal utility when the true distribution is known, while the communication requirement for exchanging the estimations among the agents can be kept to a minimal level.

Keywords

Team coordination Incomplete information Learning in Multi-agent Systems 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    A. H. Bond and L. Gasser, editors. Readings in Distributed Artificial Intelligence. Morgan Kaufmann, 1988.Google Scholar
  2. 2.
    Hung H. Bui, D. Kieronska, and S. Venkatesh. Learning other agents' preferences in multiagent negotiation. In Proceedings of the National Conference on Artificial Intelligence (AAAI-96), pages 114–119, August 1996.Google Scholar
  3. 3.
    Hung H. Bui, D. Kieronska, and S. Venkatesh. Optimal communication among team members. In Abdul Sattar, editor, Advanced Topics in Artificial Intelligence, Proceedings of the Tenth Australian Joint Conference on Artificial Intelligence, AI-97, volume 1342 of Lecture Notes in Artificial Intelligence, pages 116–126. Springer, 1997.Google Scholar
  4. 4.
    P. R. Cohen and H. J. Levesque. Intention is choice with commitment. Artificial Intelligence, 42:213–261, 1990.MATHMathSciNetCrossRefGoogle Scholar
  5. 5.
    M. L. Dowell. Learning in Multiagent Systems. PhD thesis, Department of Electrical and Computer Engineering, University of South Carolina, 1995.Google Scholar
  6. 6.
    Edmund H. Durfee and Jeffrey S. Rosenschein. Distributed problem solving and multi-agent systems: Comparisons and examples. In Proceedings of the 13th International Workshop on Distributed Artificial Intelligence (IWDAI-94), pages 94–104, 1994.Google Scholar
  7. 7.
    Piotr J. Gmytrasiewicz and Edmund H. Durfee. A rigorous, operational formalization of recursive modelling. In Proceedings of the First International Conference on Multiagent Systems (ICMAS-95), pages 125–132, San Francisco, CA, 1995.Google Scholar
  8. 8.
    Piotr J. Gmytrasiewicz and Edmund H. Durfee. Rational interaction in multiagent environments: Coordination. In submission, 1997.Google Scholar
  9. 9.
    John C. Harsanyi. Games with incomplete information played by Bayesian players 1–3. Management Science, 14:159–182,320–334,486–502, 1967–1968.MathSciNetCrossRefGoogle Scholar
  10. 10.
    Y. Lashkari, M. Metral, and P. Maes. Collaborative interface agents. In Proceedings of the National Conference on Artificial Intelligence (AAAI-94), pages 444–449, 1994.Google Scholar
  11. 11.
    H. J. Levesque, P. R. Cohen, and J. H. T. Nunes. On acting together. In Proceedings of the National Conference on Artificial Intelligence (AAAI-90), pages 94–99, 1990.Google Scholar
  12. 12.
    P. Maes and R. Kozierok. Learning interface agents. In Proceedings of the National Conference on Artificial Intelligence (AAAI-93), pages 459–465, 1993.Google Scholar
  13. 13.
    Tom M. Mitchell. Machine Learning. McGraw-Hill, New York, 1997.MATHGoogle Scholar
  14. 14.
    Roger B. Myerson. Game Theory: Analysis of Conflict. Havard University Press, 1991.Google Scholar
  15. 15.
    S. Sen, editor. Papers from the AAAI-96 Spring Symposium on Adaptation, Coevolution, and Learning in Multiagent Systems, Menlo Park, CA, March 1996. AAAI Press.Google Scholar
  16. 16.
    R. G. Smith. The contract net protocol: High-level communication and control in a distributed problem solver. IEEE Transactions on Computers, 29(12):1104–1113, 1980.Google Scholar
  17. 17.
    Milind Tambe. Towards flexible teamwork. Journal of Artficial Intelligence Research, 7:83–124, 1997.Google Scholar
  18. 18.
    Jose M. Vidal and Edmund H. Durfee. RMM's solution concept and the equilibrium point solution. In Proceedings of the 13th International Workshop on Distributed Artificial Intelligence (IWDAI-94), 1994.Google Scholar
  19. 19.
    G. Weiss and S. Sen, editors. Adaptation and Learning in Multiagent Systems, Proceedings of the IJCAI-95 Workshop. Number 1042 in Lecture Notes in Artificial Intelligence. Springer-Verlag, 1996.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Hung H. Bui
    • 1
  • Svetha Venkatesh
    • 1
  • Dorota Kieronska
    • 1
  1. 1.Department of Computer ScienceCurtin University of TechnologyPerthAustralia

Personalised recommendations