Advertisement

Abstract

We investigate systematically the impact of human intervention in the training of computer players in a strategy board game. In that game, computer players utilise reinforcement learning with neural networks for evolving their playing strategies and demonstrate a slow learning speed. Human intervention can significantly enhance learning performance, but carrying it out systematically seems to be more of a problem of an integrated game development environment as opposed to automatic evolutionary learning.

Keywords

Experimental Session Reinforcement Learn Board Game Game Stage Strategy Game 
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.

References

  1. 1.
    K. Chellapilla, D.B. Fogel (1999). “Co-Evolving Checkers Playing Programs using only Win, Lose, or Draw,” Symposium on Applications and Science of Computational Intelligence II, Vol. 3722, K. Priddy, S. Keller, D.B. Fogel, and J.C. Bezdek (eds.), SPIE, Bellingham, WA, pp. 303–312, 1999.Google Scholar
  2. 2.
    A. Condon (1992). “The Complexity of Stochastic Games”, Information and Computation 96, pp. 203–224.MATHCrossRefMathSciNetGoogle Scholar
  3. 3.
    T. Dietterich, N. Flann (1997). “Explanation-Based Learning and Reinforcement Learning: A Unified View”, Machine Learning, Vol. 28.Google Scholar
  4. 4.
    I. Ghory (2004). “Reinforcement Learning in Board Games”, Technical report CSTR-04-004, Department of Computer Science, University of Bristol.Google Scholar
  5. 5.
    H.J. van den Herik, H.H.L.M. Donkers, P.H.M. Spronck (2005). “Opponent Modelling and Commercial Games”, Proceedings of IEEE 2005 Symposium on Computational Intelligence and Games, Essex University, Colchester, UK. pp 15–25.Google Scholar
  6. 6.
    A. Junghanns, J. Schaeffer (2001). “Sokoban: Enhancing General Single-Agent Search Methods using Domain Knowledge”, Artificial Intelligence, Vol. 129, pp. 219–251.MATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    D. Kalles and P. Kanellopoulos (2001). “On Verifying Game Design and Playing Strategies using Reinforcement Learning”, ACM Symposium on Applied Computing, special track on Artificial Intelligence and Computation Logic, Las Vegas.Google Scholar
  8. 8.
    D. Kalles, E. Ntoutsi (2002). “Interactive Verification of Game Design and Playing Strategies”, IEEE International Conference on Tools with Artificial Intelligence, Washington D.C.Google Scholar
  9. 9.
    D. Kalles (2007). “Player co-modelling in a strategy board game: discovering how to play fast”, accepted for publication at Cybernetics and Systems.Google Scholar
  10. 10.
    A. Leouski (1995). “Learning of Position Evaluation in the Game of Othello”, M.Sc. Thesis, University of Massachusetts, Amherst.Google Scholar
  11. 11.
    M.L. Littman (1994). “Markov Games as a Framework for Multi-Agent Reinforcement Learning”, Proceedings of 11 th International Conference on Machine Learning, San Francisco, pp 157–163.Google Scholar
  12. 12.
    I. Partalis, G. Tsoumakas, I. Katakis and I. Vlahavas (2006). “Ensembe Pruning Using Reinforcement Learning”, Proceedings of the 4th Panhellenic conference on Artificial Intelligence, Heraklion, Greece, Springer LNCS 3955, pp. 301–310.Google Scholar
  13. 13.
    A. Samuel (1959). “Some Studies in Machine Learning Using the Game of Checkers”, IBM Journal of Research and Development, Vol. 3, pp. 210–229.CrossRefGoogle Scholar
  14. 14.
    C. Shannon (1950). “Programming a computer for playing chess”, Philosophical Magazine, Vol. 41(4), pp. 265–275.MathSciNetGoogle Scholar
  15. 15.
    R.S. Sutton (1988). “Learning to Predict by the Methods of Temporal Differences”, Machine Learning, Vol. 3, pp. 9–44.Google Scholar
  16. 16.
    R. Sutton and A. Barto (1998). “Reinforcement Learning — An Introduction”, MIT Press, Cambridge, Massachusetts.Google Scholar
  17. 17.
    G. Tesauro (1992). “Practical issues in temporal difference learning”, Machine Learning, Vol. 8, Nos. 3–4.Google Scholar
  18. 18.
    G. Tesauro (1995). “Temporal Difference Learning and TD-Gammon”, Communications of the ACM, Vol. 38, No 3.Google Scholar
  19. 19.
    S. Thrun (1995). “Learning to Play the Game of Chess”. Advances in Neural Information Processing Systems, Vol. 7.Google Scholar

Copyright information

© International Federation for Information Processing 2007

Authors and Affiliations

  • Dimitris Kalles
    • 1
  1. 1.Hellenic Open UniversityPatrasGreece

Personalised recommendations