Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Junior-Crafty hardware user experiment - 17th game

Author: Peter Berger

Date: 03:25:18 12/19/03

Go up one level in this thread


On December 19, 2003 at 06:20:19, Uri Blass wrote:

>>These lines would not be possible with the bookc.bin provided for download.
>>Yesterday I had a short conversation with another WB engine author who said that
>>testing against Crafty is mostly useless as it's only a booklearner test - so I
>>am not alone with this observation.
>
>I totally disagree.
>
>I used other programs for testing but testing is not useless.

Thanks for pointing out my sloppy wording. Of course the claim of uselessness
only applied to the default setup. Also I don't think it was intended to be a
scientific statement anyway ;).

Peter



>I am not interested in book at this point so I simply use the nunn match and I
>do not see how testing can be useless.
>
>Note that I do not think to tune the program for the nunn match and I do not
>think to change evaluation weight based on the nunn match(I do not think that it
>is a simple task even if I wanted to do it).
>
>I played 30 games of the nunn2 match against Junior5 when Junior5 used 30
>minutes against 90 minutes of Movei and the result is 15-15
>
>Another kind of test is to test the program against many programs when it gets 2
>games or 4 games against every program and again I do not find it useless.
>
>Uri



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.