Author: Gian-Carlo Pascutto
Date: 10:38:42 05/08/01
Go up one level in this thread
On May 08, 2001 at 11:57:07, Larry Proffer wrote: >2. We know about learning in computer chess. Would you tell us if it (comp-comp >learning) has any relevance at all in 'finding the best opponent for Kramnik'. Sure does. As has already been pointed out, learning is a key feature when playing matches vs humans. >Doesn't the luck involved with this bi-program learning process (remember, the >learning pathways are almost infinite - we don't know where they lead, and they >may make things worse) The good player is always lucky. If learning makes your program play worse, you have a problem that needs fixing. -- GCP
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.