Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Different test suite method?

Author: Rolf Tueschen

Date: 12:42:39 06/15/04

Go up one level in this thread


On June 15, 2004 at 15:33:41, David Dahlem wrote:

>One of the problems with the current method of testing engines with test suites
>(e.g. WM-Test) is the problem of proving that the proposed solution move is
>actually the best move, especially with positions of a positional nature.
>Perhaps a new method would avoid this problem, namely a suite of mate positions,
>with known, more easily proven solutions? Time to solution could be the criteria
>by which engines are evaluated.
>
>Just an idea. Any thoughts? Would this work?
>
>Regards
>Dave


This wouldn't work because - putting it simple - mate positions or mere tactical
ones are even worse for the estimation of a machines later game playing
strength. Here the WM test is already a step into the right direction with his
good mixture of different game parts. But it's still not good enough. 100
positions are simply too few. You should be able to test thousands if not
millions - you see the practical problem.



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.