Heuristic evaluation functions for general game playing

  • Authors:
  • James Clune

  • Affiliations:
  • Department of Computer Science, The University of California, Los Angeles

  • Venue:
  • AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 2
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

A general game playing program plays games that it has not previously encountered. A game manager program sends the game playing programs a description of a game's rules and objectives in a well-defined game description language. A central challenge in creating effective general game playing programs is that of constructing heuristic evaluation functions from game descriptions. This paper describes a method for constructing evaluation functions that represent exact values of simplified games. The simplified games are abstract models that incorporate the most essential aspects of the original game, namely payoff, control, and termination. Results of applying this method to a sampling of games suggest that heuristic evaluation functions based on our method are both comprehensible and effective.