Author: Shaun Brewer
Date: 09:11:46 03/03/99
Go up one level in this thread
On March 03, 1999 at 11:14:24, Harald Faber wrote: >On March 03, 1999 at 10:06:33, Shaun Brewer wrote: > >>I have been experimenting with openings and therefore played many games >>attempting to determine if a certain book is better or not. As my PC is needed >>for other tasks I have to interrupt the games and start again I then amalgamate >>the results of several batches of games in an attempt to get something >>statistically relevant. >> >>Here are the example scores for one such set of batches, all played on the same >>machine using the same program with books a and b constant for all batches. >> >>a b >>26 - 35 >> 9.5 - 6.5 >> 7 - 15 >>58.5 - 54.5 >>39.5 - 45.5 >> >>I am rapidly coming to the conclusion that hundreds of games would be required >>to be able to state that a is better than b, and this would also apply to >>program v program tests. > >In 2/5 a scores better so you suppose a to be better than b?? Sorry, I was not careful with my wording, in the example b is better than a when the results are amalgamated. In my conclusion I was not specifically referring to the example and should have perhaps said x is better than y to avoid the confusion. > >>What level of confidence can be attached to computer tournaments that the winner >>is the best? > >Define "best" and you get the answer. Probably the most that can be hoped for is strongest in terms of the field of opponents. > >>Is it true that computer v computer results vary more than human v human >>results? > >Talking of strong humans I'd say yes because the humans know what they play, >they play the same positions again and again so they get used to them. >Programs often have a wide opening book that leads them to positions they don't >understand. So the results are more chance than in humans play.
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.