BGonline.org Forums

Training bots on alternative starting positions

Posted By: Frank Berger
Date: Thursday, 26 November 2009, at 8:23 p.m.

In Response To: Training bots on alternative starting positions (Timothy Chow)

I've trained a net for Nackgammon some years ago. During the tests the NG net did better starting from NG and the BG net starting from BG. So far as one would expect. But during the training the difference got smaller and it seemed to converge :(

But this is at least 5 or 6 years ago and the hardware at that time wasn't that fast so the benchmarks were only a couple of 1000 games so this is not really significant. Today I use 2 million games to estimate the strength difference so the numbers above could be pure random.....

Messages In This Thread

• Training bots on alternative starting positions
  Timothy Chow -- Thursday, 26 November 2009, at 4:56 p.m.
  • Training bots on alternative starting positions
    Frank Berger -- Thursday, 26 November 2009, at 8:23 p.m.
    • Training bots on alternative starting positions
      Timothy Chow -- Friday, 27 November 2009, at 3:07 a.m.
      • Training bots on alternative starting positions
        Frank Berger -- Friday, 27 November 2009, at 7:58 p.m.
      • Training bots on alternative starting positions
        playBunny -- Sunday, 29 November 2009, at 11:24 a.m.