|
BGonline.org Forums
Training a Neural Net (like GNUBG or XG)
Posted By: Jason Lee
Date: Tuesday, 27 April 2010, at 12:02 a.m.
As I understand it, the brain of backgammon neural net is trained by giving it some rules and letting it play against itself a bajillion times, adjusting the weights along the way. The brain will converge to a strong player.
Assuming my description is correct, is there any more "NN training" going on with the brains of GNUBG and/or XG? If not, why not? A recent thread points out that XG is stronger than GNUBG... maybe GNU just needs to study some more!
JLee
|
BGonline.org Forums is maintained by Stick with WebBBS 5.12.