GP-gammon: Using genetic programming to evolve backgammon players

Yaniv Azaria, Moshe Sipper

Research output: Contribution to journalConference articlepeer-review

19 Scopus citations

Abstract

We apply genetic programming to the evolution of strategies for playing the game of backgammon. Pitted in a 1000-game tournament against a standard benchmark player - Pubeval - our best evolved program wins 58% of the games, the highest verifiable result to date. Moreover, several other evolved programs attain win percentages not far behind the champion, evidencing the repeatability of our approach.

Original languageEnglish
Pages (from-to)132-142
Number of pages11
JournalLecture Notes in Computer Science
Volume3447
DOIs
StatePublished - 1 Jan 2005
Event8th European Conference on Genetic Programming, EuroGP 2005 - Lausanne, Switzerland
Duration: 30 Mar 20051 Apr 2005

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science (all)

Fingerprint

Dive into the research topics of 'GP-gammon: Using genetic programming to evolve backgammon players'. Together they form a unique fingerprint.

Cite this