Re: [computer-go] future KGS Computer Go Tournaments - two sections?

[Don Dailey <drd@xxxxxxx>]

> I think the goal is that you don't want two (or more) basically 
> indistinguishable copies of a program playing in the same tournament.  

It's not as simple as just this.  If I put a significant amount of
effort into my program in hopes of occasionally winning a tournament,
I don't want to face the following programs in the same tournament:

  1.  GnuGo as is.
  2.  GnuGo with search added on a large network cluster.
  3.  GnuGo with search added on a single processor computer.
  4.  GnuGo with search added on a 4 processor SMP.
  5.  GnuGo with search added on an 8 processor SMP.
  6.  GnuGo with some pattern enhancements.


But there is no reason an exhibition match cannot be played with
Sluggo vs GnuGo on KGS.  Sluggo (or any other Meta-Gnu) can
experimentally verify it's good results and spur more research with
such matches.

So why not at least get SlugGo up and running on KGS?  Is there any reason
we can't do this?  It would be fun if our programs could play a few
handicap games against Sluggo.

- Don

_______________________________________________
computer-go mailing list
computer-go@xxxxxxxxxxxxxxxxx
http://www.computer-go.org/mailman/listinfo/computer-go/