In a message dated 5/10/05 10:45:07 PM Pacific Daylight Time, fotland@xxxxxxxxxxxxxxxxx writes:
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.
This is true only when the tournament is one with a single game elimination setup. This kind of tournament is not a good one to evaluate the strengths of players. A good tournament should involve some statistics.
Daniel Liu
_______________________________________________
computer-go mailing list
computer-go@xxxxxxxxxxxxxxxxx
http://www.computer-go.org/mailman/listinfo/computer-go/