[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: RE: [Bug-gnubg] User training of the Neural Nets

From: Massimiliano . Maini
Subject: RE: RE: [Bug-gnubg] User training of the Neural Nets
Date: Fri, 25 Aug 2006 09:18:33 +0200

>I'm not sure why, but I'm not getting all the e-mails from the mailing
>The one below that is quoted, never got to me for example. Anyhow, I'm
>some tests that may be of help to the developers, as well as users. Some
>time ago, Michael Depreli selected positions from a long money game
>between Snowie 3.2 and GNU 0.13, in which one bot thought a mistake had
>played. There were 626 positions in all, tested with GNU 0.12, 0.13, 0.14,
>and Snowie 3 and 4 for example. He rolled the results out to see who was
>right, and then compiled a table showing the respective results of each
>at their normal full playing strength.

Interesting work.
Which bot did the rollouts ? Which settings ?
What's the "normal full playing strength" of each bot ?


reply via email to

[Prev in Thread] Current Thread [Next in Thread]