KI - Künstliche Intelligenz

, Volume 25, Issue 1, pp 25–33 | Cite as

Knowledge-Based General Game Playing

  • Sebastian Haufe
  • Daniel Michulke
  • Stephan Schiffel
  • Michael Thielscher
Fachbeitrag

Abstract

Although we humans cannot compete with computers at simple brute-force search, this is often more than compensated for by our ability to discover structures in new games and to quickly learn how to perform highly selective, informed search. To attain the same level of intelligence, general game playing systems must be able to figure out, without human assistance, what a new game is really about. This makes General Game Playing in ideal testbed for human-level AI, because ultimate success can only be achieved if computers match our ability to master new games by acquiring and exploiting new knowledge. This article introduces five knowledge-based methods for General Game Playing. Each of these techniques contributes to the ongoing success of our FLUXPLAYER (Schiffel and Thielscher in Proceedings of the National Conference on Artificial Intelligence, pp. 1191–1196, 2007), which was among the top four players at each of the past AAAI competitions and in particular was crowned World Champion in 2006.

Keywords

General game playing Knowledge representation Fluxplayer 

References

  1. 1.
    Aloul FA, Ramani A, Markov IL, Sakallah KA (2002) Solving difficult SAT instances in the presence of symmetry. In: Design automation conference, University of Michigan Google Scholar
  2. 2.
    Amir E, Engelhardt B (2003) Factored planning. In: Proceedings of the international joint conference on artificial intelligence (IJCAI), pp 929–935 Google Scholar
  3. 3.
    Brafman R, Domshlak C (2006) Factored planning: How, when and when not. In: Proceedings of the AAAI conference on artificial intelligence, pp 809–814 Google Scholar
  4. 4.
    Clune J (2007) Heuristic evaluation functions for general game playing. In: Proceedings of the AAAI conference on artificial intelligence. AAAI Press, Vancouver, pp 1134–1139 Google Scholar
  5. 5.
    d’Avila Garcez ABKB, Gabbay D (2002) Neural symbolic learning systems. Springer, Berlin MATHGoogle Scholar
  6. 6.
    Fox M, Long D (1999) The detection and exploitation of symmetry in planning problems. In: Proceedings of the international joint conference on artificial intelligence (IJCAI), pp 956–961 Google Scholar
  7. 7.
    Gelfond M (2008) Answer sets. In: van Harmelen F, Lifschitz V, Porter B (eds) Handbook of knowledge representation. Elsevier, Amsterdam, pp 285–316 CrossRefGoogle Scholar
  8. 8.
    Günther M, Schiffel S, Thielscher M (2009) Factoring general games. In: Proceedings of the IJCAI workshop on general intelligence in game-playing agents (GIGA), pp 27–34 Google Scholar
  9. 9.
    Kelareva E, Buffet O, Huang J, Thiébaux S (2007) Factored planning using decomposition trees. In: Proceedings of the international joint conference on artificial intelligence (IJCAI), pp 1942–1947 Google Scholar
  10. 10.
    Kuhlmann G, Dresner K, Stone P (2006) Automatic heuristic construction in a complete general game player. In: Proceedings of the twenty-first national conference on artificial intelligence. AAAI Press, Boston, pp 1457–1462 Google Scholar
  11. 11.
    Michulke D, Thielscher M (2009) Neural networks for state evaluation in general game playing. In: ECML PKDD ’09: proceedings of the European conference on machine learning and knowledge discovery in databases. Springer, Berlin, pp 95–110 CrossRefGoogle Scholar
  12. 12.
    Puget JF (2005) Automatic detection of variable and value symmetries. In: van Beek P (ed) CP. Lecture notes in computer science, vol 3709. Springer, Berlin, pp 475–489 Google Scholar
  13. 13.
    Ruan J, van der Hoek W, Wooldridge M (2009) Verification of games in the game description language. J Log Comput 19(6):1127–1156 MATHCrossRefMathSciNetGoogle Scholar
  14. 14.
    Schiffel S (2010) Symmetry detection in general game playing. In: Proceedings of AAAI’10, pp 980–985 Google Scholar
  15. 15.
    Schiffel S, Thielscher M (2007) Fluxplayer: a successful general game player. In: Proceedings of the national conference on artificial intelligence. AAAI Press, Vancouver, pp 1191–1196 Google Scholar
  16. 16.
    Schiffel S, Thielscher M (2009) Automated theorem proving for general game playing. In: Proceedings of the international joint conference on artificial intelligence (IJCAI), pp 911–916 Google Scholar
  17. 17.
    Schiffel S, Thielscher M (2009) A multiagent semantics for the game description language. In: International conference on agents and artificial intelligence (ICAART). Springer, Berlin Google Scholar
  18. 18.
    Sutton RS (1988) Learning to predict by the methods of temporal differences. In: Machine learning. Kluwer Academic, Dordrecht, pp 9–44 Google Scholar
  19. 19.
    Tesauro G (1995) Temporal difference learning and td-gammon. Commun ACM 38(3):58–68 CrossRefGoogle Scholar
  20. 20.
    Thielscher M (2009) Answer set programming for single-player games in general game playing. In: Hill P, Warren D (eds) Proceedings of the international conference on logic programming (ICLP). Lecture notes in computer science, vol 5649. Springer, Pasadena, pp 327–341 Google Scholar
  21. 21.
    Thielscher M, Voigt S (2010) A temporal proof system for general game playing. In: Proceedings of the AAAI conference on artificial intelligence, pp 1000–1005 Google Scholar
  22. 22.
    Zhao D, Schiffel S, Thielscher M (2009) Decomposition of multi-player games. In: Proceedings of the Australasian joint conference on artificial intelligence, Melbourne, pp. 475–484 Google Scholar

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  • Sebastian Haufe
    • 1
  • Daniel Michulke
    • 1
  • Stephan Schiffel
    • 1
  • Michael Thielscher
    • 2
  1. 1.Department of Computer ScienceDresden University of TechnologyDresdenGermany
  2. 2.School of Computer Science and EngineeringThe University of New South WalesSydneyAustralia

Personalised recommendations