[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [computer-go] Win rate and handicap (was: Modern brute forcesearch)

On 10, Nov 2004, at 2:43 PM, Mark Boon wrote:


I won't comment about omniscient and any particular player, but in
games between SlugGo and Many Faces, we play statistically even
at 4 stones. We played games between h = 1 and h = 6, and the
winning percentages move from Sluggo winning about 80% at h = 1
to SlugGo (extrapolated from data up to h=6) looking to loose about
80% at h = 7. These bounds are weak on the high side because we
did not play that many games at 5 or 6 stones.

So, between these two programs, the 95% win rate is 4 or 5 stones.
But winning percentages in relation to stones change when you go up in
level.
As an amateur 6-dan, I believe I don't have much more than 95% chance
against an 8-dan. My personal score is still 0% against a real 7-dan even in
well over 20 games.

So your data doesn't necessarily translates to the level of an omniscient
player.
We are in perfect agreement. As I said, I have no comment on "omniscient."

It was my attempt to bring this lofty and hypothetical discussion back to
where we are today in the use of computers.



Cheers,
David



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