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. © Springer-Verlag Berlin Heidelberg 2005.
CITATION STYLE
Azaria, Y., & Sipper, M. (2005). GP-gammon: Using genetic programming to evolve backgammon players. In Lecture Notes in Computer Science (Vol. 3447, pp. 132–142). Springer Verlag. https://doi.org/10.1007/978-3-540-31989-4_12
Mendeley helps you to discover research relevant for your work.