ML Anthology

Neurogammon Wins Computer Olympiad

Gerald Tesauro
NeCo 1989 pp. 321-323
doi:10.1162/NECO.1989.1.3.321 /neco/1989/tesauro1989neco-neurogammon/

Abstract

Neurogammon 1.0 is a backgammon program which uses multilayer neural networks to make move decisions and doubling decisions. The networks learned to play backgammon by backpropagation training on expert data sets. At the recently held First Computer Olympiad in London, Neurogammon won the backgammon competition with a perfect record of five wins and no losses, thereby becoming the first learning program ever to win a tournament.

NeCo Semantic Scholar

Cite

Text

Tesauro. "Neurogammon Wins Computer Olympiad." Neural Computation, 1989. doi:10.1162/NECO.1989.1.3.321

Markdown

[Tesauro. "Neurogammon Wins Computer Olympiad." Neural Computation, 1989.](https://mlanthology.org/neco/1989/tesauro1989neco-neurogammon/) doi:10.1162/NECO.1989.1.3.321

BibTeX

@article{tesauro1989neco-neurogammon,
  title     = {{Neurogammon Wins Computer Olympiad}},
  author    = {Tesauro, Gerald},
  journal   = {Neural Computation},
  year      = {1989},
  pages     = {321-323},
  doi       = {10.1162/NECO.1989.1.3.321},
  volume    = {1},
  url       = {https://mlanthology.org/neco/1989/tesauro1989neco-neurogammon/}
}