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

Messages In This Thread

• Training a Neural Net (like GNUBG or XG)
  Jason Lee -- Tuesday, 27 April 2010, at 12:02 a.m.
  • Training a Neural Net (like GNUBG or XG)
    Daniel Murphy -- Tuesday, 27 April 2010, at 1:03 a.m.
    • Training a Neural Net (like GNUBG or XG)
      Jake Jacobs -- Tuesday, 27 April 2010, at 2:22 a.m.
      • Training a Neural Net (like GNUBG or XG)
        Ian Shaw -- Tuesday, 27 April 2010, at 6:28 a.m.
        • Training a Neural Net (like GNUBG or XG)
          Fabrice Liardet -- Tuesday, 27 April 2010, at 11:34 a.m.