On Wed, 2007-06-27 at 17:52 -0400, Chris Fant wrote: > I think the correct solution would probably have something to do with > generating an expected teritory map during your UCT simulations and > then prunning moves from the root that are in strongly owned enemy > territory (and you would also somehow need to prune moves into your > own strongly owned territory -- but that is a seperate problem because > your territory might be strongly owned BECAUSE of the move into it > that you need to make).
I did a lot with these maps with my simple monte carlo programs including early pass detection - it would pass when the map shows everything is clearly resolved. That still doesn't deal with dame though. Dame points always come out as not owned much by either side. The algorithm might be to do a simple test for dame and if it looks like a dame point and the ownership map is close to neutral, then it's probably a dame point. Maybe dame isn't that hard to detect - I don't know much about this. I haven't experimented with these maps with UCT programs, partly for the reason you stated. They have the "self-fulfilling prophecy" characteristic. - Don _______________________________________________ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
