Author: Chris Moreton
Date: 15:22:42 01/01/99
Go up one level in this thread
An approach that I am going to try is to simply update the information in the book as regards the number of wins, losses or draws that a position has led to (which are set when the program creates its book from a PGN file). I am going to apply the update to every position in the book made until the program went out of book. This way, the minimum threshold of selection can be modified to explore previously ignored positions another chance or can be raised to exploit knowledge already gained. I should stress that I am a complete amateur and I have no statistics on how effective this approach is. Chris On December 31, 1998 at 07:38:05, Inmann Werner wrote: >Hello > >Can anybody tell me how book learning works? >The principle should be, mark good moves as good and bad moves as bad. >But how can a program determine, what was a good or bad move? > >Werner
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.