Predicting pro-moves has very low correlation to strength. I think it is
next to useless. No experience but I think in this respect traditional
programs probably are better but certainly lose in strength. Cooperation
of moves is what matter not single moves.
Could be hard to come up with something. Esspecially as strongets
programs are not quite predictable on what they do.
Petri
Łukasz Lew kirjoitti:
Hi,
I was wondering what are the good (fast/accurate) ways of evaluating
program strength.
The most accurate one is to play many games against gnugo or on KGS.
But it is quite slow as many games are needed.
Another one is to have set of labeled positions (win/loss) and make
your program predict the labels. (This is what MoGo guys did)
It is much faster. But how well it is correlated with the true strength?
I had an idea to further refine this measure to predict ownership of
each intersection. This is much faster and completed games don't need
labeling.
It also converges much faster. And its easy to find type of positions
where your program predicts completely wrong.
Have anyone tried it?
Another idea is to try to predict moves in a set of (pro) games.
Is the prediction rate well correlated with program strength?
Lukasz
_______________________________________________
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/
_______________________________________________
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/
