G. Tesauro, D.C. Gondek, et al.
IBM J. Res. Dev
A description is given of Neurogammon 1.0, a complete backgammon program which uses multilayer neural networks to make move decisions and doubling decisions. The networks were trained by backpropagation on large expert data sets. Neurogammon appears to play backgammon at a substantially higher level than conventional programs. 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 any tournament.
G. Tesauro, D.C. Gondek, et al.
IBM J. Res. Dev
James E. Hanson, G. Tesauro, et al.
ACM Conference on Electronic Commerce 2003
M. Sridharan, G. Tesauro
ICMAS 2000
G. Tesauro
International Symposium on Electronic Commerce 2002