Author: Mogens Larsen
Date: 01:39:36 06/22/00
Go up one level in this thread
On June 21, 2000 at 21:40:37, Robert Hyatt wrote: >First, the 'learn value' is computed once and remains the same as I start >backing up thru the book line. If there is only one choice at a node in the >book tree, the learn value is just "averaged" in with whatever is already in >the learned value for that book move. Whenever there is more than one playable >alternative, the learn value is divided by N (N=number of playable moves only >at this node, does not include moves that are marked as never play, or that >have been learned to be never played). This decreased value is used above this >point in the tree. Okay, I think it's starting to sink in. Thank you for the article. Best wishes... Mogens
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.