[computer-go] State of the art of pattern matching
Mark Boon
tesujisoftware at gmail.com
Tue Apr 1 05:02:15 PDT 2008
On 31-mrt-08, at 20:28, Don Dailey wrote:
> You could be
> blind-siding the program.
I think this is the crux of the matter. Not just in MC but in Go
programming in general. If you add 'strong' knowledge you can create
blind-spots. For example, I guess a ko rarely gets played during
playouts because strong priority is given to connecting the stone in
atari. It's only during the actual search that ko is discovered. But
if you have a case where it's almost always out of the scope of the
search-tree to find the blind-spot of a piece of knowledge then it
can lead to very poor play.
Mark
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://computer-go.org/pipermail/computer-go/attachments/20080401/41c9c70b/attachment.htm
More information about the computer-go
mailing list