论文信息 - Neurogammon Wins Computer Olympiad

Neurogammon Wins Computer Olympiad

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.

Gerald Tesauro | G. Tesauro

[1] Geoffrey E. Hinton,et al. Learning representations by back-propagation errors, nature , 1986 .

[2] Gerald Tesauro,et al. Connectionist Learning of Expert Preferences by Comparison Training , 1988, NIPS.

[3] Terrence J. Sejnowski,et al. A Parallel Network that Learns to Play Backgammon , 1989, Artif. Intell..

[4] Richard Lippmann,et al. Review of Neural Networks for Speech Recognition , 1989, Neural Computation.

[5] Lawrence D. Jackel,et al. Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.