Learning Action Descriptions of Opponent Behaviour in the Robocup 2D Simulation Environment

  • Alberto Illobre
  • Jorge Gonzalez
  • Ramon Otero
  • Jose Santos
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6489)


The Robocup 2D simulation competition [13] proposes a dynamic environment where two opponent teams are confronted in a simplified soccer game. All major teams use a fixed algorithm to control its players. An unexpected opponent strategy, not previously considered by the developers, might result in winning all matches. To improve this we use ILP to learn action descriptions of opponent players; for learning on dynamic domains, we have to deal with the frame problem. The induced descriptions can be used to plan for desired field states. To show this we start with a simplified scenario where we learn the behaviour of a goalkeeper based on the actions of a shooter player. This description is used to plan for states where a goal can be scored. This result can directly be extended to a multiplayer environment.


ILP Action Descriptions Answer Sets Nonmonotonic Reasoning Robocup Simulation Environment 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Benson, S.: Learning action models for reactive autonomous agents. Tech. rep. CS-TR-97-1589, Ph. The., Department of Computer Science, Stanford University (1997)Google Scholar
  2. 2.
    Chen, M., et al.: RoboCup Soccer Server, Users Manual (2002)Google Scholar
  3. 3.
    Driessens, K., Jacobs, N., Cossement, N., Monsieurs, P., De Raedt, L.: Inductive verification and validation of the kULRoT roboCup team. In: Asada, M., Kitano, H. (eds.) RoboCup 1998. LNCS (LNAI), vol. 1604, pp. 193–206. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  4. 4.
    Gelfond, M., Lifschitz, V.: The Stable Model Semantics for Logic Programming. In: Proceedings of the Fifth International Conference on Logic Programming, ICLP (1988)Google Scholar
  5. 5.
    Khardon, R.: Learning to take Actions. Machine Learning 35(1) (1999)Google Scholar
  6. 6.
    Lifschitz, V.: Action languages, answer sets and planning. In: The Logic Programming Paradigm: a 25-Year Perspective. Springer, Heidelberg (1999)Google Scholar
  7. 7.
    Matsui, T., Inuzuka, N., Seki, H.: Adapting behaviour by inductive prediction in soccer agents. In: Mizoguchi, R., Slaney, J.K. (eds.) PRICAI 2000. LNCS, vol. 1886, p. 807. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  8. 8.
    McCarthy, J., Hayes, P.J.: Some philosophical problems from the standpoint of artificial intelligence. Machine Intelligence 4, 463–502 (1969)zbMATHGoogle Scholar
  9. 9.
    Moyle, S., Muggleton, S.H.: Learning programs in the event calculus. In: Džeroski, S., Lavrač, N. (eds.) ILP 1997. LNCS, vol. 1297. Springer, Heidelberg (1997)Google Scholar
  10. 10.
    Muggleton, S.H.: Inverse entailment and Progol. New Generation Computing 13, 245–286 (1995)CrossRefGoogle Scholar
  11. 11.
    Otero, R.: Embracing Causality in Inducing the Effects of Actions. In: Conejo, R., Urretavizcaya, M., Pérez-de-la-Cruz, J.-L. (eds.) CAEPIA/TTIA 2003. LNCS (LNAI), vol. 3040, pp. 291–301. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  12. 12.
    Otero, R., Varela, M.: IAction, a System for Learning Action Descriptions for Planning. In: ILP (2006)Google Scholar
  13. 13.
    RoboCup Official Site,
  14. 14.
    Stone, P., Riley, P., Veloso, M.: The CMUnited-99 champion simulator team. AI Magazine 21(3), 33–40 (2000)Google Scholar
  15. 15.
    Torrey, L., Shavlik, J., Walker, T., Maclin, R.: Skill acquisition via transfer learning and advice taking. In: Fürnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol. 4212, pp. 425–436. Springer, Heidelberg (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Alberto Illobre
    • 1
  • Jorge Gonzalez
    • 1
  • Ramon Otero
    • 1
  • Jose Santos
    • 1
  1. 1.Computer Science DepartmentUniversity of CorunnaSpain

Personalised recommendations