Author: Peter Skinner
Date: 07:38:51 01/07/06
Go up one level in this thread
On January 07, 2006 at 03:51:32, Uri Blass wrote: >It seems that all this learning is a big failure in comp-comp games(at least >against fruit). > >programs in the ssdf list fail to improve their result against fruit with more >games. > >I wonder if programmers are going to improve their learning in order to improve >their score in long matches against programs with no learning. > >Uri I would think the only time any learning feature fails is when the same game/position isn't played and new scenarios constantly come up. Learning is only of real value when repeating a win (against someone who has no learning) or to stop repeating an identical loss. If a program is using a very wide book, then same position may never be seen and render learning useless. Peter
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.