Title :
Neurogammon: a neural-network backgammon program
Abstract :
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 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
Keywords :
computer games; learning systems; neural nets; parallel architectures; Neurogammon; a neural-network backgammon program; backgammon competition; backpropagation; complete backgammon program; doubling decisions; large expert data sets; learning program; move decisions; multilayer neural networks;
Conference_Titel :
Neural Networks, 1990., 1990 IJCNN International Joint Conference on
Conference_Location :
San Diego, CA, USA
DOI :
10.1109/IJCNN.1990.137821