As I already said before, I _do_ prevent filling of single eyes (suicide moves). I thought you guys were talking about the real double eyes. Anyway the UCT version has won its first game after I extended to full length playouts. Maybe my deterministic eval that I used for early cutoffs is bad...
On Sat, Mar 26, 2011 at 12:47 PM, Christoph Birk < [email protected]> wrote: > > On Mar 26, 2011, at 9:37 AM, Daniel Shawul wrote: > >> It was a just a first implementation since I don't really know how to >> detect double eyes >> and prevent the program from filling it. >> > > random games _without_ preventing filling single eyes are meaningless. > > Christoph > > > > > _______________________________________________ > Computer-go mailing list > [email protected] > http://dvandva.org/cgi-bin/mailman/listinfo/computer-go >
_______________________________________________ Computer-go mailing list [email protected] http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
