Author: Jaime Benito de Valle Ruiz
Date: 12:14:01 02/20/04
Go up one level in this thread
>I'd be interested. It might be nice if the test suite was broken up into >different >sections. For example, a large number of positions evaluating king safety would >be useful. It might also be interesting if we had a number of unbalanced >ultra-dyanamic positions (3 minors vs. queen, 2 rooks vs. 3 minors etc.) Also >positions that had a similar theme could be enlightening. Two bishops type >positions, minor vs. minor type games, hogs on the 7th and so forth. >Obviously, this could be a *very* long list, but it should be to be really >useful. Thanks for the asnwer. Actually, I had a similar idea about having different sections depending on the "theme" (king safety, etc..), and I already have a small list. > >The other aspect of this is the information returned by the various evaluation >routines. Djinn, Crafty and many other engines list multiple components of the >evaluation routine (type "help eval" at the Djinn command line to see the >options >available). Seeing a score of +1.35 indicates the trend but doesn't give any >real detail and IMHO is of limited value. We might even decide on a minimum >set of parameters to produce and display (king safety, pawn structure, space >etc.) > >regards, >--tom I know many engines, such as Crafty split up all the components of the evaluation, but doing this manually for a long list could be quite slow; that's why I suggested making it automatic to spot "suspiciuos values". Then, you can analyze more carefully what's going on. I'll also check to see how many positions can I find and I'll post them here. Regards, Jaime
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.