Quoting Jacques Basaldúa <[EMAIL PROTECTED]>:
chrilly wrote:
The results in Go are spectacular, because the quality of
conventional evaluations is low.
There is more than that. As the proverb states "Go is a territorial
game". You win a game of go by wining points
and at the end one point is one point no matter where it is. This
accumulative nature of go is in the base of why
UCT works so well having some known inappropriate features
(E.g. ladders and many tactics, where the best move is found very
late, if at all.) I don't think this applies to
chess, but I have never tried.
Weak tactics is a problem of the playouts in my opinion. UCT as a
general search
method has thus little to do with ladders and other game specific details. If
there are no tactical mistakes in the playouts the problems disappear. Also
tactics has a large impact on where territory appears in the playout, since
much of the noise in the playouts come from tactical mistakes near the end of
the game.
In other words UCT works well when evaluation/playouts is/are strong. I
believe
there are still improvements possible to the UCT algorithm as shown by the
recent papers by Mogo and Crazystone authors, but what really will make a
difference is in the quality in the playouts.
-Magnus
_______________________________________________
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/
