• DocumentCode
    188671
  • Title

    A Pendulum Effect of Expert Playing in Games

  • Author

    Kalles, Dimitris ; Kanellopoulos, Panagiotis

  • Author_Institution
    Sch. of Sci. & Technol., Hellenic Open Univ., Patras, Greece
  • fYear
    2014
  • fDate
    10-12 Nov. 2014
  • Firstpage
    810
  • Lastpage
    814
  • Abstract
    When learning how to play a strategy board game, one can measure the relative effectiveness of the learned policies by assessing how often a player wins and how easily these wins are scored. Experimental evidence also shows that when one of the competing players is trained by a sophisticated tutor, performance benefits also flow to the opponent. We present comprehensive experimental evidence that the level of tutor effectiveness is best demonstrated by the improvement of the tutored player´s opponent, this performance change is termed the pendulum effect.
  • Keywords
    computer games; learning (artificial intelligence); competing players; expert playing; learned policies; pendulum effect; performance benefits; performance change; sophisticated tutor; strategy board game; Computers; Educational institutions; Games; Learning (artificial intelligence); Learning systems; Robots; Training; board games; function approximation; neural networks; reinforcement learning; temporal difference learning;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Tools with Artificial Intelligence (ICTAI), 2014 IEEE 26th International Conference on
  • Conference_Location
    Limassol
  • ISSN
    1082-3409
  • Type

    conf

  • DOI
    10.1109/ICTAI.2014.125
  • Filename
    6984561