Author: Frank Schneider
Date: 04:15:37 10/23/98
Go up one level in this thread
On October 22, 1998 at 17:14:19, Howard Exner wrote: >Has anyone tried this ... Running a 20 game blitz match with the same >program but labeling the one program A and the other B. So the first >game would for example have Crafty A vs. Crafty B. Then the match would >continue with Crafty B vs. Crafty A and so on. > >What would be the results after a 20 game match? What if many 20 >game matches were run like this? Could this tell us something about >the predictability of what 20 game match scores tell us? Since the >programs competing are dead equal one would suspect a 10 - 10 result. >I'm curious what might be the range of the match results. > >I tried a 10 game match like this a while ago using Rebel 8. >The results of Rebel A vs Rebel B was 6.5-3.5. I think results like this will occur often, therefore playing 20-games- matches to compare two versions of one program doesn't make much sense. I once wrote a program for a game called 'wormworld' and had to compare versions of my program. I played 200-games-matches and my experience was that I got reliable and reproducable results. Even some close (110-90) results were reproducable (for example 110-90 --> 113-87). But since Wormworld differs from chess I'm not sure if it would work for chess. And the searchtime was limited to 1 second a move which is unrealistic for chess. > >If someone has data on this could they post it. Frank
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.