Temporal difference learning applied to game playing and the results of application to Shogi

  title={Temporal difference learning applied to game playing and the results of application to Shogi},
  author={D. F. Beal and M. Smith},
  journal={Theor. Comput. Sci.},
  • D. F. Beal, M. Smith
  • Published 2001
  • Computer Science
  • Theor. Comput. Sci.
  • This paper describes the application of temporal difference (TD) learning to minimax searches in general, and presents results from shogi. TD learning is used to adjust the weights for evaluation features over the course of a series of games, starting from arbitrary initial values. For some games, to obtain weights accurate enough for high-performance play will require the TD learning phase to make use of minimax searches. A theoretical description of TD applied to minimax search is given, and… CONTINUE READING
    23 Citations

    Topics from this paper

    Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
    • 691
    • PDF
    On Learning From Game Annotations
    • 11
    First Steps Towards Learning from Game Annotations
    • 4
    • PDF
    Large-Scale Optimization for Evaluation Functions with Minimax Search
    • 34
    • Highly Influenced
    • PDF
    Learning of Piece Values for Chess Variants
    • 3
    • PDF


    Some studies in machine learning using the game of checkers
    • 572
    • PDF
    Natural Developments in Game Research
    • 29
    • PDF
    TD-Gammon, a Self-Teaching Backgammon Program, Achieves Master-Level Play
    • 766
    • PDF
    Adaptive Pattern-Oriented Chess
    • 74
    • PDF
    Shogi for beginners
    • 8
    • 25
    • PDF
    Learning Piece Values Using Temporal Differences
    • 46
    Null Move and Deep Search
    • C. Donninger
    • Computer Science
    • J. Int. Comput. Games Assoc.
    • 1993
    • 53