Advertisement

Specialized vs. Multi-game Approaches to AI in Games

  • Maciej ŚwiechowskiEmail author
  • Jacek Mańdziuk
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 322)

Abstract

In this work, we identify the main problems in which methodology of creating multi-game playing programs differs from single-game playing programs. The multi-game framework chosen in this comparison is General Game Playing, which was proposed at Stanford University in 2005, since it defines current state-of-the-art trends in the area. Based on the results from the International General Game Playing Competitions and additional results of our agent named MINI-Player we conclude on what defines a successful player. The most successful players have been using a minimal knowledge and a mechanism called Monte Carlo Tree-Search, which is simulation-based and self-improving over time.

Keywords

Games Artificial Intelligence General Game Playing Heuristic Search 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Apt, K.R., Wallace, M.: Constraint Logic Programming using Eclipse. Cambridge University Press, New York (2007)zbMATHGoogle Scholar
  2. 2.
    Browne, C., Powley, E., Whitehouse, D., Lucas, S., Cowling, P., Rohlfshagen, P., Tavener, S., Perez, D., Samothrakis, S., Colton, S.: A Survey of Monte Carlo Tree Search Methods. IEEE Transactions on Computational Intelligence and AI in Games 4(1), 1–43 (2012)CrossRefGoogle Scholar
  3. 3.
    Brügmann, B.: Monte Carlo Go. Technical report, Max Planck Institute for Physics (1993)Google Scholar
  4. 4.
    Clune, J.: Heuristic Evaluation Functions for General Game Playing. In: AAAI, pp. 1134–1139. AAAI Press (2007)Google Scholar
  5. 5.
    Epstein, S.: Toward an ideal trainer. Machine Learning 15(3), 251–277 (1994)zbMATHGoogle Scholar
  6. 6.
    Finnsson, H., Björnsson, Y.: Simulation-based approach to general game playing. In: AAAI. AAAI Press (2008)Google Scholar
  7. 7.
    d’Avila Garcez, A.S., Gabbay, D.M., Broda, K.B.: Neural-Symbolic Learning System: Foundations and Applications. Springer-Verlag New York, Inc., Secaucus (2002)Google Scholar
  8. 8.
    Genesereth, M.R., Love, N., Pell, B.: General game playing: Overview of the aaai competition. AI Magazine 26(2), 62–72 (2005)Google Scholar
  9. 9.
    Gherrity, M.: A Game-learning Machine. PhD thesis, University of California at San Diego, La Jolla, CA, USA (1993) UMI Order No. GAX94-14755Google Scholar
  10. 10.
    Hsu, F.H.: Behind Deep Blue: Building the Computer that Defeated the World Chess Champion. Princeton University Press, Princeton (2002)Google Scholar
  11. 11.
    Kaiser, D.M.: Automatic feature extraction for autonomous general game playing agents. In: Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2007, pp. 93:1–93:7. ACM, New York (2007)Google Scholar
  12. 12.
    Kishimoto, A., Schaeffer, J.: Transposition table driven work scheduling in distributed game-tree search. In: Cohen, R., Spencer, B. (eds.) Canadian AI 2002. LNCS (LNAI), vol. 2338, pp. 56–68. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  13. 13.
    Kissmann, P., Edelkamp, S.: Gamer, a General Game Playing Agent. KI 25(1), 49–52 (2011)Google Scholar
  14. 14.
    Kocsis, L., Szepesvári, C.: Bandit based Monte-Carlo planning. In: Fürnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol. 4212, pp. 282–293. Springer, Heidelberg (2006)Google Scholar
  15. 15.
    Kuhlmann, G., Dresner, K., Stone, P.: Automatic heuristic construction in a complete general game player. In: Proceedings of the Twenty-First National Conference on Artificial Intelligence, pp. 1457–1462 (July 2006)Google Scholar
  16. 16.
    Levinson, R.: Morph ii: A universal agent - progress report and proposal. Technical report, University of California at Santa Cruz, Santa Cruz, CA, USA (1994)Google Scholar
  17. 17.
    Love, N., Hinrichs, T., Haley, D., Schkufza, E., Genesereth, M.: General game playing: Game description language specication (March 2008)Google Scholar
  18. 18.
    Mańdziuk, J.: Computational Intelligence in Mind Games. In: Duch, W., Mańdziuk, J. (eds.) Challenges for Computational Intelligence. SCI, vol. 63, pp. 407–442. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  19. 19.
    Mańdziuk, J.: Knowledge-Free and Learning-Based Methods in Intelligent Game Playing. SCI, vol. 276. Springer, Heidelberg (2010)CrossRefzbMATHGoogle Scholar
  20. 20.
    Mańdziuk, J., Świechowski, M.: Generic heuristic approach to general game playing. In: Bieliková, M., Friedrich, G., Gottlob, G., Katzenbeisser, S., Turán, G. (eds.) SOFSEM 2012. LNCS, vol. 7147, pp. 649–660. Springer, Heidelberg (2012)Google Scholar
  21. 21.
    Mccarthy, J., Hayes, P.J.: Some philosophical problems from the standpoint of artificial intelligence. In: Machine Intelligence, pp. 463–502. Edinburgh University Press (1969)Google Scholar
  22. 22.
    Méhat, J., Cazenave, T.: Ary, a general game playing program. In: Board Games Studies Colloquium, Paris (2010)Google Scholar
  23. 23.
    Michulke, D., Schiffel, S.: Distance features for general game playing. In: Proceedings of the IJCAI 2011 Workshop on General Game Playing (GIGA 2011), pp. 7–14 (2011)Google Scholar
  24. 24.
    Michulke, D., Thielscher, M.: Neural networks for state evaluation in general game playing. In: Proceedings of the European Conference on Machine Learning (EMCL), pp. 95–110 (2009)Google Scholar
  25. 25.
    Nilsson, N.J.: Artificial Intelligence: A New Synthesis. Morgan Kaufmann Publishers Inc., San Francisco (1998)zbMATHGoogle Scholar
  26. 26.
    Pell, B.: Metagame: A new challenge for games and learning. In: Programming in Artificial Intellegence: The Third Computer Olympiad, pp. 237–251. Ellis Horwood Limited (1992)Google Scholar
  27. 27.
    Plaat, A., Schaeffer, J., Pijls, W., de Bruin, A.: Best-first fixed-depth minimax algorithms. Artificial Intelligence 87(1-2), 255–293 (1996)CrossRefMathSciNetGoogle Scholar
  28. 28.
    Reisinger, J., Bahceci, E., Karpov, I., Miikkulainen, R.: Coevolving strategies for general game playing. In: Proceedings of the IEEE Symposium on Computational Intelligence and Games, pp. 320–327. IEEE, Piscataway (2007)Google Scholar
  29. 29.
    Schaeffer, J.: The history heuristic and alpha-beta search enhancements in practice. IEEE Trans. Pattern Anal. Mach. Intell. 11(11), 1203–1212 (1989)CrossRefGoogle Scholar
  30. 30.
    Schiffel, S., Thielscher, M.: Fluxplayer: A successful general game player. In: Proceedings of the 22nd AAAI Conference on Artificial Intelligence (AAAI 2007), pp. 1191–1196. AAAI Press (2007)Google Scholar
  31. 31.
    Sharma, S., Kobti, Z., Goodwin, S.: Coevolving intelligent game players in a cultural framework. In: Proceedings of the IEEE Congress on Evolutionary Computing, Special Session on Computational Intelligence in Games (2009)Google Scholar
  32. 32.
    Świechowski, M., Mańdziuk, J.: Self-Adaptation of Playing Strategies in General Game Playing. IEEE Transactions on Computational Intelligence and AI in Games (2014); Accepted for publication 20/06/2013. Available in Early Access, doi: 10.1109/TCIAIG.2013.2275163Google Scholar
  33. 33.
    Tak, M.J.W., Winands, M.H.M., Bjornsson, Y.: N-grams and the last-good-reply policy applied in general game playing. IEEE Transactions on Computational Intelligence and AI in Games 4(2), 73–83 (2012)CrossRefGoogle Scholar
  34. 34.
    Walędzik, K., Mańdziuk, J.: An Automatically-Generated Evaluation Function in General Game Playing. IEEE Transactions on Computational Intelligence and AI in Games (2014); Accepted for publication 08/10/2013. Available in Early Access, doi: 10.1109/TCIAIG.2013.2286825Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Phd Studies at Systems Research InstitutePolish Academy of SciencesWarsawPoland
  2. 2.Faculty of Mathematics and Information ScienceWarsaw University of TechnologyWarsawPoland

Personalised recommendations