Automated Assistants to Aid Humans in Understanding Team Behaviors

  • Taylor Raines
  • Milind Tambe
  • Stacy Marsella
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1856)


Multi-agent teamwork is critical in a large number of agent applications, including training, education, virtual enterprises and collective robotics. Tools that can help humans analyze, evaluate, and understand team behaviors are becoming increasingly important as well. We have taken a step towards building such a tool by creating an automated analyst agent called ISAAC for post-hoc, off-line agent-team analysis. ISAAC’s novelty stems from a key design constraint that arises in team analysis: multiple types of models of team behavior are necessary to analyze different granularities of team events, including agent actions, interactions, and global performance. These heterogeneous team models are automatically acquired via machine learning over teams’ external behavior traces, where the specific learning techniques are tailored to the particular model learned. Additionally, ISAAC employs multiple presentation techniques that can aid human understanding of the analyses. This paper presents ISAAC’s general conceptual framework, motivating its design, as well as its concrete application in the domain of RoboCup soccer. In the RoboCup domain, ISAAC was used prior to and during the RoboCup’99 tournament, and was awarded the RoboCup scientific challenge award.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    André, E., Herzog, G., Rist, T. Generating Multimedia Presentations for RoboCup SoccerGames. In RoboCup-97: Robot Soccer World Cup I, 1997.Google Scholar
  2. 2.
    Balch, T. The Impact of Diversity on Performance in Multi-robot Foraging. In Proceedings of the Third Annual Conference on Autonomous Agents, 1999.Google Scholar
  3. 3.
    Bhandari, I., Colet, E., Parker, J., Pines, Z., Pratap, R., Ramanujam, K. Advanced Scout: Data Mining and Knowledge Discovery in NBA Data. In Data Mining and Knowledge Discovery, 1997.Google Scholar
  4. 4.
    Caruana, R., Freitag, D. Greedy Attribute Selection. In 11 th Proceedings of the 11 th International conference on Machine Learning (ICML), 1994.Google Scholar
  5. 5.
    Dorais, G., Bonasso, R., Kortenkamp, D., Pell, B., Schreckenghost, D. Adjustable Autonomy for Human-Centered Autonomous Systems. Working notes of the Sixteenth International Joint Conference on Artificial Intelligence Workshop on Adjustable Autonomy Systems, 1999Google Scholar
  6. 6.
    Jennings, N. Controlling Cooperative Problem Solving in Industrial Multi-agent System Using Joint Intentions. In Artificial Intelligence, Vol. 75, 1995.Google Scholar
  7. 7.
    Johnson, W. L. Agents that Learn to Explain Themselves. In Proceedings of AAAI-94, 1994.Google Scholar
  8. 8.
    Kitano, H., Tambe, M., Stone, P., Veloso, M., Noda, I., Osawa, E. & Asada, M. The RoboCup synthetic agent’s challenge. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 1997.Google Scholar
  9. 9.
    Ndumu, D., Nwana, H., Lee, L., Haynes, H. Visualization and debugging of distributed multi-agent systems. In Applied Artificial Intelligence Journal, Vol 13(1), 1999.Google Scholar
  10. 10.
    Quinlan, J. C4.5: Programs for Machine Learning. Morgan Kaufmann, 1994.Google Scholar
  11. 11.
    Reiter, E. Has a Consensus NL Generation Architecture Appeared, and is it Psycholinguistically Plausible? In Proceedings of the Seventh International Workshop on Natural Language Generation, 1994.Google Scholar
  12. 12.
    Sengers, P. Designing Comprehensible Agents. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 1999.Google Scholar
  13. 13.
    Shen, W.M., and Leng, B. A Metapattern-Based Automated Discovery Loop for Integrated Data Mining. In IEEE Transactions on Data and Knowledge Engineering, 1996.Google Scholar
  14. 14.
    Stone, P., Veloso, M. Using Decision Tree Confidence Factors for Multiagent Control. In Proceedings of the International Conference on Autonomous Agents, 1998.Google Scholar
  15. 15.
    Sycara, K., Decker, K., Pannu, A., Williamson, M., Zeng, D., Distributed Intelligent Agents. In IEEE Expert, 1996.Google Scholar
  16. 16.
    Tambe, M. Johnson, W. L., Jones, R., Koss, F., Laird, J. E., Rosenbloom, P.S., Schwamb, K. Intelligent Agents for Interactive Simulation Environments. In AI Magazine, 16(1) (Spring), 1995.Google Scholar
  17. 17.
    Tambe, M. Towards Flexible Teamwork. In Journal of Artificial Intelligence Research, Vol. 7, 1997.Google Scholar
  18. 18.
    Ting, K. Inducing Cost-Sensitive Trees via Instance Weighting. In Principles of Data Mining and Knowledge Discovery (PKDD 98), 1998.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Taylor Raines
    • 1
  • Milind Tambe
    • 1
  • Stacy Marsella
    • 1
  1. 1.Information Sciences Institute and Computer Science DepartmentUniversity of Southern CaliforniaMarina del ReyUSA

Personalised recommendations