Performance and attention in multi-agent tasks

  • Yiming Ye
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1456)


A well designed cooperation strategy for a task oriented multi-agent team is important as it can improve performance. A challenging research issue in cooperation concerns the extent to which an agent should pay attention to the actions and effects of other agents. In this paper, we address this issue in the context of an object search team. We first propose the concept of an activity window which captures an agent's view of the activities and effects of the team. Then we pinpoint some criteria that can be used to determine whether it is beneficial for an agent to put an action of the team into its window. Finally, we present experimental results to test these criteria.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    B. Hayes-Roth, L. Brownston, and R. Gen. Multiagent collabration in directed improvisation. In Proceedings of the International Conference on Multi-Agent Systems (ICMAS-95), 1995.Google Scholar
  2. 2.
    T. Hogg and B. Huberman. Controlling chaos in distributed systems. IEEE Transactions on Systems, Man, and Cybernetics, 21(6), 1991.Google Scholar
  3. 3.
    J. Kephart, T. Hogg, and B. Huberman. Dynamics of computational ecosystems: implications for DAI. Distributed Artificial Intelligence, Volume 2, Research Notes in Artificial Intelligence, Pitman, 1989.Google Scholar
  4. 4.
    H. Kitano, M. Asada, Y. Kuniyoshi, I. Noda, and E. Osawa. The robot world cup initiative. In Proceedings of IJCAI-95 Workshop on Entertainment and AI/Alife, 1995.Google Scholar
  5. 5.
    K. Pimentel and K. Teixeira. Virtual reality: through the new looking glass. Windcrest/McGraw-Hill, Blue Ridge Summit, 1994.Google Scholar
  6. 6.
    A. Rao, A. Lucas, D. Morley, S. M., and M. G. Agent-oriented architecture for aircombat simulation. Technical Report Technical Note 42, The Australian Artificial Intelligence Institute, 1993.Google Scholar
  7. 7.
    S. Sen, S. Roychowdhury, and N. Arora. Effects of local information on group behavior. In Proceedings of Second International Conference on Multi-Agent Systems, pages 315–321, Kyoto, Japan, 1996.Google Scholar
  8. 8.
    M. Tambe and P. Rosenbloom. Resc: An approach for real-time, dynamic agent tracking. In Proceedings of the International Joint Conference on Artificial Intelligence, 1995.Google Scholar
  9. 9.
    J. Vidal and E. Durfee. Recursive agent modeling using limited rationality. In Proceedings of the International Conference on Multi-Agent Systems (ICMAS-95), 1995.Google Scholar
  10. 10.
    Y. Ye. Sensor Planning for Object Search. PhD thesis, Department of Computer Science, University of Toronto, Toronto, Canada, January 1997.Google Scholar
  11. 11.
    Y. Ye and J. K. Tsotsos. On the collaborative object search team: a formulation. In Distributed Artificial Intelligence Meets Machine Learning, Lecture Notes in Artificial Intelligence Vol. 1221, Gerhard WeiB Ed., pages 94–116, 1997.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Yiming Ye
    • 1
  1. 1.IBM T.J. Watson Research CenterYorktown HeightsUSA

Personalised recommendations