Author: Fernando Villegas
Date: 15:40:59 10/26/98
Go up one level in this thread
On October 26, 1998 at 13:43:18, Ed Schröder wrote: >>Can someone explain to me the different learning functions among the top >>contenders? book learning? How do each work and which method is most effective? > >>-Rebel 10(esp interested in this) >>-MChess >>-Fritz/Junior >>-Crafty >>-Genius > >>Thanks in advance > >The main principle in Rebel is "weights". When losing a game then lower >the weight. When a game is won increase the weight. All Rebel book moves >have a "weight" value which serves 2 purposes: > >1) the weight value is used to play book moves random. >2) the weight value is a strong indication to favor a move or not. > >The effect is that Rebel will avoid lost book lines and repeat the book >lines it has won. > >- Ed - Hi Ed: If I did not understand bad, this system means Rebel will not play anymore a line not because this line is flawed, BUT because he was not capable of getting good results with it. If that is the thing, then Rebel is not learning to play better, but just avoiding paths where he misshandles the game. This is more a neurotic behaviour than a learning one. So, in the long run, what we'll have will be not a more knowleadgable program ,but a more restricted one, a narrow minded program stuck just with the liones he plays well qwith his actuial programming. I think -although I know there is a great abysm between words and implementation- that real learning should mean some kind of changes within the source code. Fernando
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.