On Sun, 2007-04-08 at 11:24 +0200, Heikki Levanto wrote: > > In fact this is how beginners think about the game. It doesn't > > seem to me like a good learning aid to try to get the computers > > to "emulate" the losing strategy weaker players use. > > Weaker players can not estimate the score until very late in the game. > Not with enough precision, anyway. Thus, most of the time they have no > idea if they are winning or loosing by 0.5 points.
But the whole idea is to take you PAST this level of understanding. > Then the most obvious > strategy must be to maximize your score, so that even in case of an > error in the evaluation or an error in the endgame, the result would > still be favourable. Again, this is probably a good strategy for beginners, but the idea is to get you beyond this point. That's why we are talking about a program that you can LEARN from. LEARN means get better. So perhaps it is the case that a dumbed down version is better initially, but may not help you get past this conceptual barrier. > This ought to apply to computer programs too, as > long as we have much uncertainty in the evaluation functions. But it doesn't. I have not seen where maximizing the total won territory has improved a program. It's more important to actually understand what is going on - map out specifically what you need to win and not worrry about anything else. You should fight for the win and this is not a difficult concept - this will make you much better. - Don _______________________________________________ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
