Author: Jay Scott
Date: 13:23:37 02/25/98
Go up one level in this thread
On February 25, 1998 at 13:06:36, Amir Ban wrote: >I've also done some work on this. It seems that the most natural >probability mapping is: 1 / (1 + exp(-x/c)), where x is your eval and c >a suitable positive constant for scaling. It meets the necessary >boundary conditions and symmetry requirements. I'd have to go reread the original papers to be sure, but if I remember right this is the map used by Bill and many of the later othello programs. http://forum.swarthmore.edu/~jay/learn-game/systems/othello.html There's no need to invent this stuff from scratch; it's already been done. Adapting it for chess programs is enough work. :-) Jay
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.