Alain wrote: > - the original MC used mean_score/standard_deviation as criterion > I understand why it is a good thing. > I found that std/mean is internal coherency factor > Is this equivalent to choosing the winning probability? (i guess no, but > i have doubts)
It is equivalent under the assumption that the sampled scores are normally distributed. That is of course an incorrect assumption but I figured that the ratio should have a good chance to be meaningful anyway. /Gunnar _______________________________________________ gnugo-devel mailing list [email protected] http://lists.gnu.org/mailman/listinfo/gnugo-devel
