Author: Russell Reagan
Date: 13:57:04 08/24/03
Go up one level in this thread
On August 24, 2003 at 13:12:14, Jorge Pichard wrote: >http://www.chessbase.com/newsdetail.asp?newsid=1141 This doesn't seem very interesting to me, as it seems like a bunch of meaningless statistics. I was hoping that he would take all kinds of factors, such as the losses of computer programs to FIDE ranked human players. It is very probable that perfect chess ends in a draw. The only difference between a draw and a win to a computer is how well the opponent played (this is different with humans, where they might be tired for examlpe and are content with a draw). The computer just spits out what it thinks is the best move. His list, based largely (or totally?) on statistics doesn't account for things like this. I think a much better list would be one that takes things like losses into heavy consideration, because to me a program that has never lost to a human is more impressive to me than one who might have a better winning percentage. I also agree that the sample pool is very small, to the point where statistics are meaningless. I also don't think it's fair to basically other programs that haven't had the chance to play Kasparov. Every program on his list might well draw with Kasparov, given the chance. His list seems more like the "which programs have played the strongest opponents without making fools of themselves" list.
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.