In message
<[email protected]>, steve
uurtamo <[email protected]> writes
:)
my point was that simply totaling total "won by" points after each
game is over, or totalling total "won by" points divided by ten after
each game should produce the same rank order of results, therefore not
punishing anyone.
I don't understand this. It sounds as if you will tell the bots that
their games will be scored one way, then you will actually score them a
different way.
my comment that one handicap difference in strength, in an even game,
roughly equates to 10 game stones at the end of the game, was perhaps
too distracting as a rationale (perhaps because it is only empirically
true at the kyu level?).
Isn't 10 too low, even for bots? My guess is, about 15 for strong
players, about 13 for current bots.
the idea that i like about keeping track of number of points won or
lost by is that not only could you find the winner, but you could find
how absolutely dominant, on average, they were against their
opponents. if the variance was low, we might expect to see, say, a
less than 20 stone average advantage in points. normalizing by
dividing by 10 just scales this down to something "chunkier".
I disagree. You won't find anything meaningful unless the bots all know
what game they are playing. And if they do all know what game they are
playing, you won't find anything useful by scoring the results on some
other basis.
Nick
--
Nick Wedd [email protected]
_______________________________________________
computer-go mailing list
[email protected]
http://www.computer-go.org/mailman/listinfo/computer-go/
