Author: Rolf Tueschen
Date: 03:04:57 01/20/06
Go up one level in this thread
On January 20, 2006 at 05:51:32, Martin Andersen2 wrote: >On January 20, 2006 at 05:28:47, Rolf Tueschen wrote: > > > >>I question that Rybka is already proven the strongest engine today. Then people >>tell me to look at CEGT where that has been proven... This was a few days ago >>here in CCC. I must object to such sort of hybris. The truth is that we dont >>have statistical methods for making such claims. Even after 700 or maybe over >>1000 games the significance is not so sure and if you look at the +/- boundaries >>of the so called Elo results then you still have overlappings and you cant say >>that Rybka is the clear first. > >Rybka 1.0 beta 64 bit 2859 +-21 >Deep shredder 9 2CPU 2804 +-17 > >So Rybka's number 1 spot cannot be touched. You are wrong. > >Martin. 1 Rybka 1.01 Beta 9 64-bit opt 2921 73 68 71 80.3 % 2677 33.8 % 2 Rybka 1.0 Beta 64-bit 2859 21 21 765 68.4 % 2725 32.7 % 3 Deep Shredder 9.12 x64 2CPU 2844 45 45 168 64.6 % 2740 30.4 % These are the overall results in CEGT with ALL games. You can easily see that the results are overlapping by a large margin. Just take 2921 and subtract 68 and then take 2844 and add 45... If you now object with the other list then please let's clarify how all these lists were created. I would say already after a short look that you cant compare a prog with 700 games and the others with already 3000. The latter have a seeming stability which makes no sense, because we have artifical entities and NOT real systems from mother nature. And dont forget what I discussed with Bob - namely the Rybka is in a daily update loop while the other programs, also Shredder, dont have that advantage... So far about artifical creations.
This page took 0.01 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.