Rapid Game Strategy Evaluation Using Fuzzy Extreme Learning Machine

  • YingJie Li
  • Peter Hiu Fung Ng
  • Simon Chi Keung Shiu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8251)


Interactions among game units can be conveniently described by fuzzy measures and integrals. Focusing on Warcraft, there are several good results of unit selection strategy evaluation for a genetic algorithm that search in plan space. However, this kind of evaluators are suffered from high complexity in fuzzy measure determination. In this paper, we novelly combine Extreme Learning Machine(ELM) and Fuzzy Integral(FI) to achieve a fast evaluation of game strategy. Experimental comparison demonstrates the effectiveness of the proposed method in both time and accuracy.


  1. 1.
    Li, Y.J., Ng, H.F., Wang, H.B., Li, Y., Shiu, C.K.S.: Applying fuzzy integral for performance evaluation in real time strategy game. In: Proceedings of 2010 2nd International Conference on Information and Multimedia Technology (ICIMT 2010), Hong Kong, China, pp. 28–30 (December 2010)Google Scholar
  2. 2.
    Li, Y.J., Ng, H.F.P., Wang, H.B., Shiu, C.K.S., Li, Y.: Apply different fuzzy integrals in unit selection problem of real time strategy game. In: 2011 IEEE International Conference on Fuzzy Systems (FUZZ), pp. 170–177. IEEE (2011)Google Scholar
  3. 3.
    Aha, D.W., Molineaux, M., Ponsen, M.: Learning to win: Case-based plan selection in a real-time strategy game. In: Muñoz-Ávila, H., Ricci, F. (eds.) ICCBR 2005. LNCS (LNAI), vol. 3620, pp. 5–20. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  4. 4.
    Hsieh, J.L., Sun, C.T.: Building a player strategy model by analyzing replays of real-time strategy games. In: IEEE International Joint Conference on Neural Networks, IJCNN 2008, IEEE World Congress on Computational Intelligence, pp. 3106–3111. IEEE (2008)Google Scholar
  5. 5.
    Hagelbäck, J., Johansson, S.J.: A multi-agent potential field based bot for a full rts game scenario. Proceedings of Artificial Intelligence and Interactive Digital Entertainment, AIIDE (2009)Google Scholar
  6. 6.
    Sugeno, M.: Theory of fuzzy integrals and its applications (1974)Google Scholar
  7. 7.
    Wang, Z., Yang, R., Lee, K.H., Leung, K.S.: The choquet integral with respect to fuzzy-valued signed efficiency measures. In: 2008 IEEE International Conference on Fuzzy Systems, pp. 2143–2148. IEEE (2008)Google Scholar
  8. 8.
    Narukawa, Y.: Modeling decisions: information fusion and aggregation operators. Springer (2007)Google Scholar
  9. 9.
    Huang, G.B., Wang, D.H., Lan, Y.: Extreme learning machines: a survey. International Journal of Machine Learning and Cybernetics 2(2), 107–122 (2011)CrossRefGoogle Scholar
  10. 10.
    Wang, J., Wang, Z.J.: Using neural networks to determine sugeno measures by statistics. Neural Networks 10(1), 183–195 (1997)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • YingJie Li
    • 1
  • Peter Hiu Fung Ng
    • 1
  • Simon Chi Keung Shiu
    • 1
  1. 1.Department of ComputingThe Hong Kong Polytechnic UniversityKowloonHong Kong

Personalised recommendations