Author: Sandro Necchi
Date: 07:06:47 01/01/05
Go up one level in this thread
On January 01, 2005 at 08:51:45, Harald Faber wrote: >On January 01, 2005 at 07:46:46, Sandro Necchi wrote: > >>On January 01, 2005 at 07:40:58, Harald Faber wrote: >> >>>On December 31, 2004 at 15:21:23, Sandro Necchi wrote: >>> >>>>Again I agree. Some years ago there was no learning/book learning at all and >>>>that was a big missing...which made a big difference with the human players. >>>>Now that we have them we need to improve the learning features and not to turn >>>>them off! >>> >>> >>>There is danger that one might test the best learner. >> >>Yes, but I think a chess program is a chess player and so it should be tested in >>the best mode, suggested by the programmer, and without removing anything. >>The learning feature is part of the program. >>Sandro > > >True, but for analysis reasons I do not find it acceptable to let the program >play dozens or even hundreds of games to let it learn before I get accurate >results. I understand, but the SSDF list is the most accurate results system. Any otehr system is not that accurate to me...just my opinion. SSDF have changed the way to test sometimes in the past, as agreed between them, to avoid getting higher scores by new programs due to new available features. I agree with their system as they are testing at long time controls and with the best settings as advised by the programmers. Do not say that I say this because Shredder is first in the list, because I always said so. Complains? Yes, I wished they would test Shredder 8 UCI in tournament mode and with Shredder 8a book, but they have rules they apply to all programs to test and I understand this. Regards Sandro
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.