Author: Daniel Shawul
Date: 22:51:02 10/04/05
Go up one level in this thread
On October 04, 2005 at 20:02:37, Jon Dart wrote: >On October 04, 2005 at 19:23:49, Joachim Rang wrote: > > >>what has this to do with book-learning? > >I have two kinds of book learning. One is opening >learning based on scores during the game. Then there >is a separate learning pass based on game result. >They are independent. The first strategy avoids >lines that give a bad score soon out of book. But >sometimes these are not actually bad openings. The >second strategy avoids lines that lead to lost games. > >--Jon If Arsan is +5.0 against engine x but loses because of time problem, are you going to save this as lost for Arsan in positional learning? I think that you should not save game result in this case. If you do positional learning like many do by storing the search result of a positon at a given depth, and then filling the hashtable with this data at startup, it will avoid bad lines and favour good ones. Daniel
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.