Advertisement

Training a Pac-Man Player with Minimum Domain Knowledge and Basic Rationality

  • Bo Yuan
  • Cheng Li
  • Wei Chen
Part of the Communications in Computer and Information Science book series (CCIS, volume 93)

Abstract

In this paper, a Pac-Man player (agent) is trained based on four neural networks. The motivation is to demonstrate how computational intelligence techniques can be used to simulate the self-learning process of human players with minimum prior knowledge about the game and basic rationality in their behaviors. Experimental results show that, on a simplified version of the original Pac-Man game, the agent can achieve reasonable scores after only a handful of trials. This performance is in contrast to existing work on evolving Pac-Man agents where thousands of trials and huge amount of computational efforts are typically required.

Keywords

Pac-Man Neural Networks Games Computational Intelligence 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Chellapilla, K., Fogel, D.: Evolving an Expert Checkers Playing Program without Using Human Expertise. IEEE Transactions on Evolutionary Computation 5(4), 422–428 (2001)CrossRefGoogle Scholar
  2. 2.
    Fogel, D.: Blondi24: Playing at the Edge of AI. Morgan Kaufmann, San Francisco (2002)Google Scholar
  3. 3.
    Gallagher, M., Ledwich, M.: Evolving Pac-Man Players: Can We Learn from Raw Input? In: IEEE Symposium on Computational Intelligence and Games, pp. 282–287 (2007)Google Scholar
  4. 4.
    Gallagher, M., Ryan, A.: Learning to Play Pac-Man: An Evolutionary, Rule-Based Approach. In: Congress on Evolutionary Computation, pp. 2462–2469 (2003)Google Scholar
  5. 5.
    Koza, J.: Genetic Programming: On the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge (1992)zbMATHGoogle Scholar
  6. 6.
    Lucas, S.: Evolving a Neural Network Location Evaluator to Play Ms. Pac-Man. In: IEEE Symposium on Computational Intelligence and Games, pp. 203–210 (2005)Google Scholar
  7. 7.
    Robles, D., Lucas, S.: A Simple Tree Search Method for Playing Ms. Pac-Man. In: IEEE Symposium on Computational Intelligence and Games, pp. 249–255 (2009)Google Scholar
  8. 8.
    Szita, I., Lõrincz, A.: Learning to Play Using Low-Complexity Rule-Based Policies: Illustrations through Ms. Pac-Man. Journal of Artificial Intelligence Research 30(1), 659–684 (2007)zbMATHGoogle Scholar
  9. 9.
    Uston, K.: Mastering Pac-Man. Signet (1981)Google Scholar
  10. 10.
    Wirth, N., Gallagher, M.: An Influence Map Model for Playing Ms. Pac-Man. In: IEEE Symposium on Computational Intelligence and Games, pp. 228–233 (2008)Google Scholar
  11. 11.
    Online Pac-Man Game, http://www.neave.com/games/pacman
  12. 12.

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Bo Yuan
    • 1
  • Cheng Li
    • 1
  • Wei Chen
    • 1
  1. 1.Intelligent Computing Lab, Division of Informatics, Graduate School at ShenzhenTsinghua UniversityShenzhenP.R. China

Personalised recommendations