Chris Fant wrote: >>> I suspect that for very long time controls we would be better off >>> turning UCT (with, say 10K playouts) into an evaluation function and >>> then using alpha-beta on top of it. >>> >>> Álvaro. >>> >> This is very interesting to me. Not the memory management part, but >> the fact that you believe the tree is not being grown optimally (if that >> is what you are saying.) >> > > > I thought his point was that with an alpha-beta layer on top of the > UCT layer, you can do much longer searches because you are throwing > away the large UCT tree after each evaluation of an AB tree node. > I'm not sure he proposes this as a solution to the memory problem or whether he believes it creates a tree with a better shape.
It might turn out that this is a good practical solution to the memory problem but I don't think in principle it's a very good thing all by itself. However, I wonder if a kind of super selective alpha-beta search can be constructed that adheres to the same (basic) principles that are working for us with these GO programs. - Don > _______________________________________________ > computer-go mailing list > computer-go@computer-go.org > http://www.computer-go.org/mailman/listinfo/computer-go/ > > _______________________________________________ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
