BGonline.org Forums

XG training and NN question

Posted By: Tom Keith
Date: Sunday, 1 August 2010, at 6:53 p.m.

In Response To: XG training and NN question (Timothy Chow)

If you train a bot to play Snake, I'm guessing one of the following will happen:

(1) The bot will play Snake ok, but won't be good at other types of back games, or

(2) The bot will never become good at Snake because the number of followup positions is so large.

Now, it's possible that neural nets aren't the right algorithm for superbackgames.

That's quite likely. It's remarkable that NNs work as well as they do on normal backgammon positions.

Messages In This Thread

• XG training and NN question
  Leonardo Jerkovic -- Sunday, 1 August 2010, at 2:31 a.m.
  • XG training and NN question
    eXtreme Gammon -- Sunday, 1 August 2010, at 3:06 a.m.
    • XG training and NN question
      Timothy Chow -- Sunday, 1 August 2010, at 3:31 a.m.
      • XG training and NN question
        Klaus Evers -- Sunday, 1 August 2010, at 4:30 a.m.
      • XG training and NN question
        Tom Keith -- Sunday, 1 August 2010, at 1:48 p.m.
        • XG training and NN question
          Timothy Chow -- Sunday, 1 August 2010, at 5:33 p.m.
          • XG training and NN question
            Leonardo Jerkovic -- Sunday, 1 August 2010, at 6:27 p.m.
            • XG training and NN question
              Timothy Chow -- Sunday, 1 August 2010, at 10:43 p.m.
          • XG training and NN question
            Tom Keith -- Sunday, 1 August 2010, at 6:53 p.m.
            • XG training and NN question
              Timothy Chow -- Sunday, 1 August 2010, at 10:46 p.m.
              • XG training and NN question
                mtuhtan -- Sunday, 1 August 2010, at 11:58 p.m.
                • XG training and NN question
                  Leonardo Jerkovic -- Monday, 2 August 2010, at 12:33 a.m.
    • XG training and NN question
      neilkaz -- Sunday, 1 August 2010, at 3:36 a.m.
    • V2 feature request
      KenB -- Sunday, 1 August 2010, at 6:09 p.m.