On Tue, 2008-08-12 at 08:43 +0200, Gian-Carlo Pascutto wrote: > > I don't like opening books. They are a liability when the rest of the > program is still improving so quickly.
I had one that worked effectively, but had to be redone if the program improved substantially, so it was a program. I essentially deep-search each new position encountered. So each game played presented a new book position to learn which I did off-line. It even had variety - I didn't want it too predictable so I deep searched N times, and used the moves in the same ratio they were chosen. Usually only 1 or 2 moves get played. I stopped searching N times when the probability of an opponent being able to get you to some position on purpose went below 1%. Then I still deep searched but only 1 time. That worked quite well. It doesn't always play great moves, but it is like increasing the level substantially for a few moves and saving a lot of time. I'm not sure which helped the most. It's an unsatisfying way to build a book and so I agree with you. It is tied to the power of the computer you are running on (if you upgrade your computer the benefit of the book is reduced) and if you upgrade your program you must recompute the book. - Don _______________________________________________ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
