[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Bug-gnubg] Alternative weights files and call for benchmarkers
From: |
Joseph Heled |
Subject: |
Re: [Bug-gnubg] Alternative weights files and call for benchmarkers |
Date: |
Mon, 25 Jun 2012 20:56:53 +1200 |
Hi again,
While the benchmark shows the new net(s) are better than the old, one must remember the improvement in playing ability is not large.
In 1 million 5 point matches between the two, the new net wins in 50.084% of the matches. This result is not even strongly significant, at about 2 sigma.
Also, the new crashed net is still hopeless at advancing a prime from the deep. Until it does a reasonable job there, I see little hope for gnubg advancing to the next level in the crashed area.
Here is an example. Unfortunately gnubg can't import this file because the Board: is unsupported. Perhaps someone can look into this? (My own fibs2html handles this fine. but it is very old by now)
-Joseph
Score is 0-0 in a 1 point match.
gnu0plyX is X - gnu0plyO is O
Board: -10 0 0 2 2 2 2 2 2 1 1 1 0 0 0 0 0 0 0 0 0 0 -1 0
O: (5 4) 21-16 20-16
X: (1 5) 23-22 22-17
O: (1 2) 16-15 16-14
X: (5 5) 17-12
O: (5 3) 25-20 20-17
X: (4 6) can't move
O: (5 1) 21-16 17-16
X: (6 6) can't move
O: (3 3) 19-16 19-16 14-11 11-8
X: (2 3) can't move
O: (1 1) 20-19 19-18 18-17 17-16
X: (2 3) can't move
O: (6 4) 14-10 8-2
X: (3 6) 12-6 6-3
O: (2 4) 15-13 15-11
X: (6 1) 3-0 1-0
O: (5 2) 17-15 16-11
X: (1 3) 1-0 1-0
O: (6 2) 17-15 13-7
X: (6 4) 1-0 1-0
O: (2 2) 16-14 11-9 10-8 8-6
X: (4 4) 1-0 1-0 1-0 1-0
O: (5 2) 16-14 6-1
X: (6 1) 1-0
X: wins 2 points