Neural Networks for State Evaluation in General Game Playing

  • Daniel Michulke
  • Michael Thielscher
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5782)

Abstract

Unlike traditional game playing, General Game Playing is concerned with agents capable of playing classes of games. Given the rules of an unknown game, the agent is supposed to play well without human intervention. For this purpose, agent systems that use deterministic game tree search need to automatically construct a state value function to guide search. Successful systems of this type use evaluation functions derived solely from the game rules, thus neglecting further improvements by experience. In addition, these functions are fixed in their form and do not necessarily capture the game’s real state value function. In this work we present an approach for obtaining evaluation functions on the basis of neural networks that overcomes the aforementioned problems. A network initialization extracted from the game rules ensures reasonable behavior without the need for prior training. Later training, however, can lead to significant improvements in evaluation quality, as our results indicate.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bader, S., Hitzler, P.: Dimensions of neural-symbolic integration — a structured survey. In: We Will Show Them: Essays in Honour of Dov Gabbay. Kings College Publications, pp. 167–194 (2005)Google Scholar
  2. 2.
    Clune, J.: Heuristic evaluation functions for general game playing. In: Proceedings of the AAAI National Conference on Artificial Intelligence, Vancouver, pp. 1134–1139. AAAI Press, Menlo Park (2007)Google Scholar
  3. 3.
    d’Avila Garcez, A., Broda, K., Gabbay, D.: Neural Symbolic Learning Systems. Springer, Heidelberg (2002)CrossRefMATHGoogle Scholar
  4. 4.
    d’Avila Garcez, A., Zaverucha, G., de Carvalho, L.: Logical inference and inductive learning in artificial neural networks. In: Proceedings of the ECAI Workshop on Neural Networks and Structured Knowledge (1996)Google Scholar
  5. 5.
    Fawcett, T.: Feature Discovery for Problem Solving Systems. PhD thesis, University of Massachusetts, Amherst (1993)Google Scholar
  6. 6.
    Finnsson, H.: Cadia-player: A general game playing agent. Master’s thesis, School of Computer Science, Reykjavík University (2007)Google Scholar
  7. 7.
    Finnsson, H., Björnsson, Y.: Simulation-based approach to general game playing. In: Proceedings of the AAAI National Conference on Artificial Intelligence, Chicago, pp. 259–264. AAAI Press, Menlo Park (2008)Google Scholar
  8. 8.
    Genesereth, M., Love, N., Pell, B.: General game playing: Overview of the AAAI competition. AI Magazine 26, 62–72 (2005)Google Scholar
  9. 9.
    Hölldobler, S., Kalinke, Y.: Towards a massively parallel computational model for logic programming. In: Proceedings of the ECAI Workshop on Combining Symbolic and Connectionist Processing, pp. 68–77 (1994)Google Scholar
  10. 10.
    Hsu, F.: Behind Deep Blue: Building the Computer that Defeated the World Chess Champion. Princeton University Press, Princeton (2002)MATHGoogle Scholar
  11. 11.
    Kuhlmann, G., Dresner, K., Stone, P.: Automatic Heuristic Construction in a Complete General Game Player. In: Proceedings of the AAAI National Conference on Artificial Intelligence, Boston, pp. 1457–1462. AAAI Press, Menlo Park (2008)Google Scholar
  12. 12.
    Love, N., Hinrichs, T., Haley, D., Schkufza, E., Genesereth, M.: General Game Playing: Game Description Language Specification. Technical Report LG–2006–01, Stanford Logic Group, Computer Science Department, Stanford University, 353 Serra Mall, Stanford, CA 94305 (2006), http://games.stanford.edu
  13. 13.
    Schiffel, S., Thielscher, M.: Fluxplayer: A successful general game player. In: Proceedings of the AAAI National Conference on Artificial Intelligence, Vancouver, pp. 1191–1196. AAAI Press, Menlo Park (2007)Google Scholar
  14. 14.
    Hitzler, P., Bader, S., Witzel, A.: Towards a massively parallel computational model for logic programming. In: Proceedings of the IJCAI Workshop on Neural-Symbolic Learning and Reasoning (2005)Google Scholar
  15. 15.
    Tesauro, G.: Temporal difference learning and TD-gammon. Communications of the ACM 38, 58–68 (1995)CrossRefGoogle Scholar
  16. 16.
    Towell, G., Shavlik, J., Noordenier, M.: Refinement of approximate domain theories by knowledge based neural network. In: Proceedings of the AAAI National Conference on Artificial Intelligence, pp. 861–866 (1990)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Daniel Michulke
    • 1
  • Michael Thielscher
    • 1
  1. 1.Department of Computer ScienceDresden University of TechnologyGermany

Personalised recommendations