Mixture of Expert Used to Learn Game Play (original) (raw)

Abstract

In this paper, we study an emergence of game strategy in multiagent systems. Symbolic and subsymbolic approaches are compared. Symbolic approach is represented by a backtrack algorithm with specified search depth, whereas the subsymbolic approach is represented by feed-forward neural networks that are adapted by reinforcement temporal difference TD(λ) technique. We study standard feed-forward networks and mixture of adaptive experts networks. As a test game, we used the game of simplified checkers. It is demonstrated that both networks are capable of game strategy emergence.

Preview

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Sutton, R.S.: Learning to predict by the method of temporal differences. Machine Learning 3, 9–44 (1988)
    Google Scholar
  2. Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
    Google Scholar
  3. Tesauro, G.J.: Practical issues in temporal difference learning. Machine Learning 8, 257–277 (1992)
    MATH Google Scholar
  4. Tesauro, G.J.: TD-gammon, a self-teaching backgammon program achieves master-level play. Neural Computation 6(32), 215–219 (1994)
    Article Google Scholar
  5. Tesauro, G.: Temporal difference learning and td-gammon. Communications of the ACM 38(3), 58–68 (1995)
    Article Google Scholar
  6. Pollack, J., Blair, A., Land, M.: Coevolution of a backgammon player. In: Langton, C.G. (ed.) Proc. of Artificial Life V, pp. 92–98. MIT Press, Cambridge (1996)
    Google Scholar
  7. Chellapilla, K., Fogel, D.B.: Evolving neural networks to play checkers without expert knowledge. IEEE Trans. Neural Networks 10(6), 1382–1391 (1999)
    Article Google Scholar
  8. Chellapilla, K., Fogel, D.B.: Evolution, neural networks, games, and intelligence. Proc. IEEE 87(9), 1471–1496 (1999)
    Article Google Scholar
  9. Chellapilla, K., Fogel, D.B.: Evolving an expert checkers playing program without using human expertise. IEEE Transactions on Evolutionary Computation 5(4), 422–428 (2001)
    Article Google Scholar
  10. Zaman, R., Wunsch III, D.: TD methods applied to mixture of experts for learning 9x9 go evaluation function. In: IJCNN 1999 vol. 6, pp. 3734–3739 (1999)
    Google Scholar
  11. Jordan, M., Jacobs, R.: Modular and hierarchical learning systems. The Handbook of Brain Theory and Neural Networks. MIT Press, Cambridge (1995)
    Google Scholar

Download references

Author information

Authors and Affiliations

  1. Institute of Applied Informatics Faculty of Informatics and Information technologies, Slovak University of Technology, Ilkovičova 3, 842 16, Bratislava
    Peter Lacko & Vladimír Kvasnička

Authors

  1. Peter Lacko
  2. Vladimír Kvasnička

Editor information

Véra Kůrková Roman Neruda Jan Koutník

Rights and permissions

© 2008 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Lacko, P., Kvasnička, V. (2008). Mixture of Expert Used to Learn Game Play. In: Kůrková, V., Neruda, R., Koutník, J. (eds) Artificial Neural Networks - ICANN 2008. ICANN 2008. Lecture Notes in Computer Science, vol 5163. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87536-9\_24

Download citation

Keywords

These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Publish with us