1125 is a great result. Gnubg contact benchmarks at about 1122, so your net is 
pretty much as good as gnubg. 1 point of contact-benchmark error is about 156.5 
micropoints/game advantage.

We've managed to get as low as 1073 with the standard 250 inputs, but it took a 
512 hidden nodes to do it, which would kill performance if we used it in the 
production gnubg.

Are you prepared to discuss your extra inputs?


n  Ian


From: [email protected] 
[mailto:[email protected]] On Behalf Of 
Øystein Schønning-Johansen
Sent: 12 February 2012 16:39
To: Mark Higgins
Cc: [email protected]
Subject: Re: [Bug-gnubg] "Joseph-ID" in benchmark db


2012/2/12 Mark Higgins <[email protected]<mailto:[email protected]>>
My best player (TD trained, race & contact networks, a couple extra inputs 
beyond the standard Tesauro ones) has an average error of 0.0164ppg/move in the 
contact set, so not surprisingly worse than GNUbg (I assume 1125 means 
0.01125ppg/move?).


No, I mean total error over the file.

> grep -e '^m ' contact.bm<http://contact.bm> | wc -l
107485

1125 is the total error over all these 107485 positions. That makes an average 
error of 0.010466577 Equity points pr positon in the 
contact.bm<http://contact.bm> file.

-Øystein

_______________________________________________
Bug-gnubg mailing list
[email protected]
https://lists.gnu.org/mailman/listinfo/bug-gnubg

Reply via email to