It might be interesting to see how Rémi Coulom's move predictor does
on these positions.
Erik
You can now donwload it as a GTP engine from the page of the paper:
http://remi.coulom.free.fr/Amsterdam2007/
Rémi
I updated the game situation figures and included Crazy
Patterns curve to the average scores figure
http://users.tkk.fi/eseurane/tmp/summary.pdf
If I'll hear no objections I'll replace the old version
(http://users.tkk.fi/eseurane/EGC2007/summary.pdf).
I must say the gogui analyze feature support thingy is quite
amazing, I guess I'll just _have to_ familiarize myself with GTP...
Remi: it would be nice, if one could change the amount of simulations,
altough I guess it has to be rather small so that those several hundred
of games mentioned in your paper can be processed in reasonable time.
Well... perhaps the available computing time doesn't matter that much,
at least for GNU go more computing time doesn't necessary help:
http://users.tkk.fi/eseurane/tmp/GNU.eps
-Esa
_______________________________________________
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/
