On Sat, Jan 26, 2019 at 10:42:10AM +0100, Øystein Schønning-Johansen wrote:
Thanks for your effort Philippe. Your numbers looks correct.
However, I think it is important to state some more details.
First: Are the games played to completion? Or are the games terminated at
race or bearoff or ...
Second: Does the pubeval evaluate all the position classes? I once did the
mistake in a similar experiment where the pubeval player actually used a
full bearoff look up table.
And then: These are cubeless moneygames I assume. These are not one-point
matches.
(Another potential bug is the opening roll. I guess that it is taken care
of.)
I didn't use gnubg + some changes, but the gnubg-nn tools from Joseph
Heled, so that should be cubeless games without bearoff databases and,
at least, directly comparable to gnubg's 2012 numbers.
gnu_pubeval_bug.pdf