Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Check with Eduard

Author: Robert Hyatt

Date: 20:06:26 06/26/01

Go up one level in this thread


On June 26, 2001 at 14:29:25, Uri Blass wrote:

>
>It also cannot be repeated against a chess program if it remembers the game and
>has learning by position or if it is not deterministic.
>
>Uri


This doesn't work quite like you think.  For lots of well-known reasons.  The
most important is that if you go out of book very early, and don't see anything
bad happening for a long while, it will take a _long_ while to propogate those
scores back up the search tree to avoid a bad early move that doesn't lose for
(say) 20 more moves.  Even more problematic is the issue known as "hung on a
local maximum value".  This type of learning is not guaranteed to solve the
problem.  Otherwise you could take Crafty, and have it "learn" wild7 and
eventually play it perfectly.  It won't happen for the reason I gave, although
it took a couple of people months of trying before they finally recognized
this.




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.