On 5/1/07, Peter Drake <[EMAIL PROTECTED]> wrote:
Like most of the UCT programs (I believe), Orego adds one tree node per
Monte Carlo run. At present, this node includes data from the run that
created it. Thus, after the first run, my tree looks like this:
ROOT: 1/1 wins
CHILD A: 1/1 wins
Ignoring the other children, I eventually do another run through that child,
getting this:
ROOT: 1/2 wins
CHILD A: 1/2 wins
GRANDCHILD B: 0/1 wins
Let's see if I get this.
You have a just added a grandchild so does that mean that all children
of root have been explored? If not, why do you add a grandchild?
Here I would expect to see CHILD B expanded, not some grandchild.
My concern here is that that there have been two runs recorded in node A and
only one in node B. Does this cause a problem for the UCT formula, which
assumes that the number of runs through a node is the sum of the number of
runs through the children?
Don't you determine the sum of visits by adding all values in the
children? I guess it looks like a nice speedup to get the sum directly
from their parent, but does that really matter in comparison to the
playout complexity?
Best,
Erik
_______________________________________________
computer-go mailing list
[email protected]
http://www.computer-go.org/mailman/listinfo/computer-go/
