On 9-okt-08, at 17:39, Don Dailey wrote:
On Thu, 2008-10-09 at 15:20 -0400, [EMAIL PROTECTED] wrote:
Computers + random = can of worms.
What if I get a fast benchmark by implementing the fastest, most
awful, random number generator imaginable? What if every one of my
"random" playouts looks the disturbingly similar?
As to the relevance, the time-eaters in my heavy playouts are
different from the time-eaters in my light playouts.
This is true, but it goes back to the well understood fact that you
cannot have a perfect benchmark.
I think this would be very useful and very relevant, just not
perfect.
Random numbers IS an issue. I required transparency so that any issue
like this can be observed, reviewed, criticized, etc.
Random numbers may just be one of the issues. There could be other
tricks that speed things up but deteriorate play in a way that's hard
to detect.
What could be an interesting way to tackle is to have a robot player
that plays a fixed number of playouts according to a known algorithm.
As benchmark you can use the computing time another algorithm (or
language) needs to attain a 50% score against it.
But it may be a bit too academic to actually realize a benchmark like
this.
Mark
_______________________________________________
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/
