From: Heikki Levanto <[EMAIL PROTECTED]>
> I still think it a bit strange that on an empty board, a program can
> prefer a 3-3 point in one corner, and in another corner find it quite
> unplayable.
It makes sense of the space evaluated by the random playouts differed. But my
thinking
is, what if it were possible to combine the information from symmetrical plays?
Better yet, perform evalutations of moves within regions, as humans do with
joseki
and life-and-death analysis, to constrain the search to smaller portions of the
tree?
I guess my experiment would only make sense for pure MC evaluations, or
other systems where each move is evaluated equally often (say, UCT after
the first move). Probably more hazzle than it is worth.
But I would still like to know how many MC evaluations it would take
until all corners look at least somewhat similar... I bet that is many
more than we see used currently - if it ever gets there.
- Heikki
--
Heikki Levanto "In Murphy We Turst" heikki (at) lsd (dot) dk
_______________________________________________
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/
____________________________________________________________________________________
Sick sense of humor? Visit Yahoo! TV's
Comedy with an Edge to see what's on, when.
http://tv.yahoo.com/collections/222_______________________________________________
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/
