Author: Frank Schneider
Date: 22:31:48 07/28/00
Go up one level in this thread
On July 25, 2000 at 14:12:46, Tom Kerrigan wrote: >It would be nice to make a change to your evaluation function and get immediate, >accurate feedback. > >So my idea is to get a huge collection of positions of known value (i.e., "white >has a stronger position") and then see how well the known values correlate to >the evaluation function's scores. Hi Tom, I'm sorry I can't provide such data, but please tell me if you have a collection like this :-) One way to generate it: most commercial programs can replay and analyze games and you can save the results including scores. You could even generate data of various engines and compare them. > >Does anybody have any ideas for getting a high-quality collection of such >positions? Or any comments on this approach in general? In general: if you compare a searchresult with a static eval result, the eval will be tuned to work well without search ;-) I think the approach can help to find positions where your eval differs most from the 'correct' score of good programs. Frank > >-Tom
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.