It seems it would not be that hard to set up cgos-like environments
where participants offer up more than one version of their program:
some play quickly, and some are allowed to take longer. ELO levels
can be set for some to correspond to mean values obtained on the
normal cgos.
Cheers,
David
On 30, Jan 2007, at 10:33 AM, terry mcintyre wrote:
This is why, much as I appreciate the value of the scalability
study now
being done, in which I am participating, it will be even more
valuable to
run a study against a variety of opponents. Of course that is
easier said
than done, alas.
_______________________________________________
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/
