• Publications
  • Influence
Learning Piece Values Using Temporal Differences
  • 45
  • 6
An analysis of minimax
  • 36
  • 5
Temporal difference learning applied to game playing and the results of application to Shogi
This paper describes the application of temporal difference (TD) learning to minimax searches in general, and presents results from shogi. Expand
  • 23
  • 5
Experiments with the null-move
  • 50
  • 4
This paper presents a model for which lookahead can be shown beneficial under some conditions for minimax search using a heuristic evaluation function. Expand
  • 30
  • 4
Temporal Coherence and Prediction Decay in TD Learning
This paper describes improvements to the temporal difference TD(λ) learning method, which leads to better learning (i.e. faster and less subject to the effects of noise) than the standard form. Expand
  • 16
  • 3
  • PDF
Temporal Difference Learning for Heuristic Search and Game Playing
We show that temporal coherence produces faster learning than earlier methods, and that TD learning can produce values that are superior to standard values for specified search regimes without any domain-specific information or human assistance. Expand
  • 26
  • 2
Random Evaluations in Chess
  • 15
  • 2
A Generalised Quiescence Search Algorithm
  • D. F. Beal
  • Mathematics, Computer Science
  • Artif. Intell.
  • 1 April 1990
This paper describes how the concept of a null move may be used to define a generalised quiescence search applicable to any minimax problem. Expand
  • 76
  • 1
Heuristic Programming in Artificial Intelligence
The first Soviet Computer Olympiad 2nd Computer OlympIad reports Go intellect wins two gold medals in the game of Go. Expand
  • 66
  • 1