Author: Thorsten Czub
Date: 22:27:08 03/05/01
Go up one level in this thread
On March 05, 2001 at 20:59:05, Dann Corbit wrote: >If you are trying to produce a reproducable experiment, then you don't change >the parameters as you go. If you just want a fun contest, then do whatever you >want. icca tournaments are fun contests ? i thought it is about world computer chess champion title too. >So, what are the goals? That should determine the conduct during the contest. to measure the strength of the program, not to measure the influence of a bug or to find out about older versions. the tournament is not an experiment made to reproduce data. its made for me to find out about the engines by watching them. i do believe that experiments do not measure the things outside as they are, but measure the things you wanted to measure before. you want to catch reality by doing circumstances that do not exist in real tournaments ?
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.