Author: Gian-Carlo Pascutto
Date: 18:45:45 07/31/05
Go up one level in this thread
On July 31, 2005 at 20:02:19, George Tsavdaris wrote: >>On July 31, 2005 at 19:17:47, Uri Blass wrote: >> >>I think that there is one problem that prevent accurate rating for Shredder. >>Programs need to play also against stronger opponents to get accurate >>rating(otherwise players who are stronger against weaker opponents but weaker >>against stronger opponents never meat the stronger opponents and get too high >>rating). > >Very nice observation.......! > And we have even more on this: Some SSDF-list engines have become so old that >the newer Shredder versions (and Junior/Fritz) are crushing them by >36-4,35.5-4.5,37-3. And this leads to many inaccuracies on the caclulated ELO of >the stronger engines, as these results are almost worthless for the >determination of how stronger a new version has become over its >predecessor...... > > With the exploding evolution of the number of new Chess engines, it's obvious >that SSDF(that has to play hundreds of games and with classic time controls too) >can't follow, so the list more and more becomes, less accurate at the higher >levels......... I don't see how A follows from B here. The SSDF could let the strongest engines play more games against each other rather than against weaker engines. The time control is of zero relevance. -- GCP
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.