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

[Marco Scheurer <marco@xxxxxxxx>]

> Let me try to explain with a though experiment.  Let's say, without  
> any
> data, that Many Faces of Go can beat Gnugo 70% of the time in 100's  
> of test
> games.  Both programs can randomize openings, and Many Faces  
> learns, so it
> won't lose the same way twice.  I'd be willing to enter a  
> tournament against
> one copy of Gnugo, expecting a 70% chance of winning.  I would not be
> willing to enter a tournament against 10 copies of gnugo.  It is  
> almost
> certain that I would not win this tournament.
Are you sure? With each copy of GNU Go having a 50% chance against  
other copies and 30% against MFOG?

> I don't understand how anyone can think that this is fair.
(But note that I've never been advocating entering N copies of any  
program.)

> Marco, if you were in a race against someone, would it be fair to  
> let him
> race twice, on different days, and use his best time against your  
> single
> time?  How about if he was allowed to train between the races, so it
> wouldn't be the "same" person?
That's not the same thing at all.

I bet there must several programs based on Monte Carlo Go. The  
algorithm is so simple that they should all be considered derivatives  
of Bouzy's original. How would you, could you stop them from  
competing? Maybe you don't care because they are much worse than  
MFOG, but why would it be a different treatment?

I believe that unless the GNU Go team principals explicitely  
disagrees, derivatives such as SlugGo should be allowed.

This is still subject to qualification. I'm not saying that N copies  
of GNU Go should be entered by anyone who knows how to install one.  
GNU Go should only be entered by its authors. But SlugGo is not GNU  
Go and I believe it deserves the right to enter a tournament against  
both GNU Go, MFOG and other top programs. It is sufficiently  
different, promising, original, and so on to qualify, in my opinion.

If SlugGo is disqualified you will have an open division with  
meaningless results because, according to what has been said until  
now, commercial programs would not dare to enter such a crowded  
field. And you will have a top division with tainted results because  
some top contenders are arbitrarily missing. And I don't understand  
why anyone would not welcome the opportunity to fight against all the  
best programs. If I were working on an engine (which I am, but sooooo  
far from anything) I would welcome a fight against both SlugGo and  
GNU Go....

marco



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