Author: GuyHaworth
Date: 01:48:24 11/01/04
Go up one level in this thread
Why not ask GT directr? http://www.research.ibm.com/massive/tdl.html#about_the_author My understanding is that ANNs work better for backgammon than for games which do not have the 'smoothing' effect (on the position evaluation function) caused by randomness. Meel Velliste and I ran an ANN-experiment on KPK some years back, somewhat helped by GT's papers. g
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.