Predicting Opponent Actions by Observation

  • Agapito Ledezma
  • Ricardo Aler
  • Araceli Sanchis
  • Daniel Borrajo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3276)


In competitive domains, the knowledge about the opponent can give players a clear advantage. This idea lead us in the past to propose an approach to acquire models of opponents, based only on the observation of their input-output behavior. If opponent outputs could be accessed directly, a model can be constructed by feeding a machine learning method with traces of the opponent. However, that is not the case in the Robocup domain. To overcome this problem, in this paper we present a three phases approach to model low-level behavior of individual opponent agents. First, we build a classifier to label opponent actions based on observation. Second, our agent observes an opponent and labels its actions using the previous classifier. From these observations, a model is constructed to predict the opponent actions. Finally, the agent uses the model to anticipate opponent reactions. In this paper, we have presented a proof-of-principle of our approach, termed OMBO (Opponent Modeling Based on Observation), so that a striker agent can anticipate a goalie. Results show that scores are significantly higher using the acquired opponent’s model of actions.


  1. 1.
    Aler, R., Borrajo, D., Galván, I., Ledezma, A.: Learning models of other agents. In: Proceedings of the Agents 2000/ECML 2000 Workshop on Learning Agents, Barcelona, Spain, June 2000, pp. 1–5 (2000)Google Scholar
  2. 2.
    Druecker, C., Duddeck, C., Huebner, S., Neumann, H., Schmidt, E., Visser, U., Weland, H.-G.: Virtualweder: Using the online-coach to change team formations. Technical report, TZI-Center for Computing Technologies, University of Bremen (2000)Google Scholar
  3. 3.
    Kitano, H., Tambe, M., Stone, P., Veloso, M., Coradeschi, S., Osawa, E., Matsubara, H., Noda, I., Asada, M.: The robocup synthetic agent challenge. In: Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence (IJCAI 1997), San Francisco, CA, pp. 24–49 (1997)Google Scholar
  4. 4.
    Ledezma, A., Aler, R., Sanchis, A., Borrajo, D.: Predicting opponent actions in the robosoccer. In: Proceedings of the 2002 IEEE International Conference on Systems, Man and Cybernetics (October 2002)Google Scholar
  5. 5.
    Ledezma, A., Berlanga, A., Aler, R.: Automatic symbolic modeling of co-evolutionarily learned robot skills. In: Mira, J., Prieto, A.G. (eds.) IWANN 2001. LNCS (LNAI), vol. 2084, pp. 799–806. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  6. 6.
    Ledezma, A., Berlanga, A., Aler, R.: Extracting knowledge from reactive robot behaviour. In: Proceedings of the Agents 2001/Workshop on Learning Agents, Montreal, Canada, pp. 7–12 (2001)Google Scholar
  7. 7.
    Nie, A.G., Honemann, A., Pegam, A., Rogowski, C., Hennig, L., Diedrich, M., Hugelmeyer, P., Buttinger, S., Steffens, T.: the osnabrueck robocup agents project. Technical report, Institute of Cognitive Science, Osnabrueck (2001)Google Scholar
  8. 8.
    Quinlan, J.R.: C4.5: Programs for Machine Learning. Morgan Kaufmann, San Mateo (1993)Google Scholar
  9. 9.
    Quinlan, J.R.: Combining instance-based and model-based learning. In: Proceedings of the Tenth International Conference on Machine Learning, Amherst, MA, June 1993, pp. 236–243. Morgan Kaufmann, San Francisco (1993)Google Scholar
  10. 10.
    Riley, P., Veloso, M.: On Behavior Classification in Adversarial Environments. In: Distributed Autonomous Robotic Systems, vol. 4, pp. 371–380. Springer, Heidelberg (2000)Google Scholar
  11. 11.
    Riley, P., Veloso, M.: Planning for distributed execution through use of probabilistic opponent models. In: Proceedings of the Sixth International Conference on AI Planning and Scheduling, AIPS-2002 (2002)Google Scholar
  12. 12.
    Riley, P., Veloso, M., Kaminka, G.: Towards any-team coaching in adversarial domains. In: Proceedings of th First International Joint Conference on Autonomous Agents and Multi-Agent Systems, AAMAS (2002)Google Scholar
  13. 13.
    Steffens, T.: Feature-based declarative opponent-modelling in multi-agent systems. Master’s thesis, Institute of Cognitive Science Osnabrück (2002)Google Scholar
  14. 14.
    Stone, P., Riley, P., Veloso, M.: Defining and using ideal teammate and opponent agent models. In: Proceedings of the Twelfth Innovative Applications of AI Conference (2000)Google Scholar
  15. 15.
    Stone, P., Veloso, M., Riley, P.: The CMUnited-98 champion simulator team. In: Asada, M., Kitano, H. (eds.) RoboCup 1998. LNCS (LNAI), vol. 1604, pp. 61–76. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  16. 16.
    Stone, P., Veloso, M., Riley, P.: The CMUnited 1998 champion simulator team. In: Asada, M., Kitano, H. (eds.) RoboCup 1998. LNCS (LNAI), vol. 1604, pp. 61–76. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  17. 17.
    Takahashi, Y., Edazawa, K., Asada, M.: Multi-module learning systemfor behavior acquisition in multi-agent environment. In: Proceedings of the 2002 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 927–931 (2002)Google Scholar
  18. 18.
    Webb, G., Kuzmycz, M.: Feature based modelling: A methodology for producing coherent, consistent, dynamically changing models of agents’s competencies. User Modeling and User Assisted Interaction 5(2), 117–150 (1996)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Agapito Ledezma
    • 1
  • Ricardo Aler
    • 1
  • Araceli Sanchis
    • 1
  • Daniel Borrajo
    • 1
  1. 1.Universidad Carlos III de MadridLeganés (Madrid)Spain

Personalised recommendations