Computer Chess Club Archives




Subject: Re: When to do a null move search - an experiment

Author: Tord Romstad

Date: 08:12:22 04/26/04

Go up one level in this thread

On April 26, 2004 at 09:31:51, Dan Andersson wrote:

> If you want to do a systematic investigation you should have a version that
>does nullmove always and saves the result together with all vital statistics
>(make sure it is only those known before nullmove is made) about the position.
> Then it would be fairly easy to make a decision tree that correlates to
>beneficial nullmove conditions.

Yes, something like this would be interesting to try.  I have often used similar
techniques to tune other types of pruning.  Thanks for the suggestion!


This page took 0.02 seconds to execute

Last modified: Thu, 07 Jul 11 08:48:38 -0700

Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.