Author: Bert van den Akker
Date: 12:40:06 07/26/00
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. > >Does anybody have any ideas for getting a high-quality collection of such >positions? Or any comments on this approach in general? > >-Tom t the end of each opening line in the 5 books of the encyclopaedia of chess openings you will find an indication how good the end position of the line is equal, white stands slightly beter etc. Some of the opening lines are very long so you will also get middle game positions. An other way is a method like the opening position tree of Frits and REBEL. If in an opening line the succes rate for white in a position is 65% for 1000 Grandmaster games which have reached this position then the change that this position is good for white is high. BvdA
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.