Author: Bruce Moreland
Date: 13:24:34 09/05/99
Go up one level in this thread
On September 05, 1999 at 12:23:27, walter irvin wrote: >i think there is also something else to considder. if program A beats program B >say 2500 to 50 .then program B beats program C 4500 to 250 .then program C beats >program A 8000 to 0 .then can you say for certain who is really stronger?? >i think you need results against all kinds different players . Yes, I was using a definition of "stronger" that is too simply, the definition I was using is simply that if A beats B > 50% of the time, A is stronger than B. It isn't necessarily valid to do any computer vs computer testing to see if one computer is stronger against humans, and certainly it's possible that there could be this kind of circle in computer vs computer, making it hard to test that as well. bruce
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.