> concentrate move searches in those areas. After analyzing about 70 > dan-level games on KGS I've found a very strong correlation to the number of > moves made in these boundary areas.
How does the correlation vary by move number? I.e. I'm guessing it is best in early middlegame; but does it also nicely find the remaining interesting areas in the endgame? Also how is the variance by game; by which I mean does it tend to work well on certain kinds of games (e.g. quiet games) and poorly on others (e.g. games with lots of invasions and life/death problems); or does it work about equally well on all games? I guess you'll need more than 70 games (and more variety of game record sources) to judge that. > merit. Possible applications could include: > ... Yes, all of those are of interest if you have something that is useful, and quick to calculate (and not too complex to code up). (I bet I'm not the only one on this list whose first go program was based on influence calculations; it'd be somehow warm and comforting to have a reason to try it again ;-) Darren -- Darren Cook http://dcook.org/mlsn/ (English-Japanese-German-Chinese free dictionary) http://dcook.org/work/ (About me and my work) http://dcook.org/work/charts/ (My flash charting demos) _______________________________________________ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
