Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Tactical speed and test suites

Author: Robert Hyatt

Date: 08:05:06 06/08/98

Go up one level in this thread


On June 08, 1998 at 05:18:16, Jouni Uski wrote:

>If we compare programs A and B in tactical test suite (WAC) and A solves
>293 positions with average solution time 5 sec, but B solves 298 with
>average speed 60 sec - so which one is better tactically? I think
>it's quite a problem to define.

I think you first have to use the same time limit.  And even then, it's
not clear what solving such positions has to do with the game of chess.
IE I have seen several material-only test engines that do well on the
suite since the goal is to win material or mate the opponent.  Don
Beal's
first null-move program did quite well with no evaluation at all other
than
counting pieces, for example.

Most of us have been running WAC for several years, and everyone has
been
using 1 minute as the normal time limit.  That's pretty long by today's
standards, but it maintains compatibility with results from 2-3 years
ago.

I can produce results for any time limit you'd like, however, to start a
new time limit...



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.