> > We have a kludge I am not proud of. I hope to improve upon it soon. > > We have been busy trying to make up for all the lost time rather than > > trying to change features that may be ugly but work well enough for > > now. > > My solution was to build an opening book :) > > It has its pros and cons; I can talk about it more if people want to > hear details.
I'm cross-posting from this thread in the computer-go list to gnugo-devel. GNU Go's opening weaknesses seem to me to be: (1) a tendency to make bad tenuki's. This problem is not special to the opening, but it is often in the opening that GNU Go plays away from an urgent position to take a big point somewhere else. (2) GNU Go doesn't really understand the importance of making a base. (That is, an extension along the side where eyes are most easily gotten.) If a stone is approached from one side, extending on the other is reflexive but GNU Go doesn't understand this principle. In case it is not clear what I mean, in the following example, moves 6, 9 and 12 are important moves because they are extensions from a stone that is approached on one side to create a base. Of course GNU Go would play 9 (because it is Joseki). But that is beside the point. GNU Go doesn't really understand this principle. (;GM[1]FF[3] RU[Japanese]SZ[19]HA[0]KM[5.5] PW[White] PB[Black] GN[White (W) vs. Black (B)] DT[2005-03-31] SY[Cgoban 1.9.14]TM[30:00(5x1:00)];B[pp];W[dd];B[pd] ;W[dp];B[fq];W[cn];B[dr];W[cq];B[iq];W[qj];B[qm];W[qg] ) If these two defects are addressed, the opening play would be stronger. For the first, it would be good to have a measure of the local temperature. That is, with play restricted to a particular area, what is the difference between the valuation between a W move there and a B move? If it is large, then a move in that area is urgent. This is not a test that GNU Go makes, but it would be not hard to implement in GNU Go, and trivial in a metamachine such as GoFigure or SlugGo. For the second point, the usual approach with GNU Go would be to add some patterns. But for a metamachine, it might be more important if the value of having a base were taken into account in the valuation of the board. Dan _______________________________________________ gnugo-devel mailing list [email protected] http://lists.gnu.org/mailman/listinfo/gnugo-devel
