BGonline.org Forums

Maybe there's a better way to measure takes?

Posted By: NJ
Date: Sunday, 18 October 2009, at 5:14 p.m.

In Response To: Maybe there's a better way to measure takes? (Phil Simborg)

I think Fabrice Liardet gave the best answer to the question, which is that the recube vig is score dependent and the neural nets are not.

Consider for the moment 6 or fewer piece bearoff positions. GNU has a 2-sided bearoff database for these positions calculated for money games. That means it can play perfectly in these positions, because it already precalculated the proper checker play and cube decision for every remaining position for both sides (like a perfect rollout).

But this 2 sided database doesn't work for matches. If you play a match, I believe GNU doesn't use the 2 sided database's play, but instead does the normal N-ply search. In order to have a correct database for a match, you would need one database for each possible score. For example if you were playing a 15 point match, you'd need over 100 databases.

As for the neural nets calculating the recube vig, you could also train 100+ neural nets. Or, perhaps, you could have match equities as inputs into one neural net and have it calculate the recube vig based on the position and match score. But I don't know how well that would work.

Messages In This Thread

• Maybe there's a better way to measure takes?
  Phil Simborg -- Sunday, 18 October 2009, at 1:58 a.m.
  • Maybe there's a better way to measure takes?
    Timothy Chow -- Sunday, 18 October 2009, at 3:15 a.m.
    • My thoughts on your responses
      Phil Simborg -- Sunday, 18 October 2009, at 2:53 p.m.
      • My thoughts on your responses
        Stick -- Sunday, 18 October 2009, at 3:01 p.m.
      • My thoughts on your responses
        Rich Munitz -- Sunday, 18 October 2009, at 7:07 p.m.
        • My thoughts on your responses
          Daniel Murphy -- Sunday, 18 October 2009, at 7:37 p.m.
          • My thoughts on your responses
            Rich Munitz -- Monday, 19 October 2009, at 3:29 a.m.
            • My thoughts on your responses
              Daniel Murphy -- Monday, 19 October 2009, at 5:24 a.m.
              • My thoughts on your responses
                Phil Simborg -- Monday, 19 October 2009, at 1:21 p.m.
                • My thoughts on your responses
                  Peter G. -- Monday, 19 October 2009, at 3:08 p.m.
  • Maybe there's a better way to measure takes?
    Matt Cohn-Geier -- Sunday, 18 October 2009, at 3:36 a.m.
  • Maybe there's a better way to measure takes?
    Andreas -- Sunday, 18 October 2009, at 8:36 a.m.
  • Maybe there's a better way to measure takes?
    Fabrice Liardet -- Sunday, 18 October 2009, at 9:40 a.m.
    • Maybe there's a better way to measure takes?
      Timothy Chow -- Sunday, 18 October 2009, at 2:22 p.m.
      • Maybe there's a better way to measure takes?
        Fabrice Liardet -- Sunday, 18 October 2009, at 3:58 p.m.
  • Maybe there's a better way to measure takes?
    Stick -- Sunday, 18 October 2009, at 1:15 p.m.
  • Maybe there's a better way to measure takes?
    Fabrice Liardet -- Sunday, 18 October 2009, at 1:37 p.m.
  • Maybe there's a better way to measure takes?
    Ian Shaw -- Sunday, 18 October 2009, at 4:12 p.m.
    • Maybe there's a better way to measure takes?
      MaX -- Thursday, 22 October 2009, at 12:31 p.m.
  • Maybe there's a better way to measure takes?
    NJ -- Sunday, 18 October 2009, at 5:14 p.m.
  • Maybe there's a better way to measure takes?
    Keene -- Monday, 19 October 2009, at 4:33 p.m.
  • Maybe there's a better way to measure takes?
    Daniel Murphy -- Monday, 19 October 2009, at 6:14 p.m.