[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
RE: computer-go: Discarding the rubbish moves
Hi,
I've actually been doing some experiments with neural networks and so
far the best net trained classifies the next move in a test set of
pro games, on average, in the top 19% of moves available. So using this
network to 'score' all available moves I could reasonably cut out ~80%
of those moves and then conduct further analysis on the remaining moves
in more detail. In practice I have used the net to remove 90% or more
due to resource limitations.
I've used it in combination with minimax search and various rough eval
functions. Playing 9x9 test games against GNUGo (3.0.0) the program
achieves a score average of -10 points with the most favourable
configurations (this does include some wins :)). None of the eval
functions are complex, just simple such as stone counting, liberty
counting or Bouzy's 5/21 influence algorithm.
Just thought you might be interested to know some practical experiment
results, and I'd be very interested to hear if anyone else has results
from similar experiments...
Julian Churchill
> This is one of those places where my net-trained reflex is to admit
> that YMMV. But your mileage would have to vary a *lot* to get to 3%.
> As an AGA 3 dan looking at pro games, I don't feel sure I can quickly
> predict that the next move will be in one of <10 places, which is what
> I'd expect if I were automatically classifying all but 3% (of moves on
> a 19x19 board) as not worth considering. I doubt computers are going
> to do better than human 3 dans on this until computers play, overall,
> much much better than 3 dans. (I appeal to the computer chess history,
> and general engineering good sense, to justify this claim. We can
> teach computers to do sophisticated classification, but usually what
> they really shine at is exploring many simpler classifications very
> fast.)
>
> --
> William Harold Newman <william.newman@xxxxxxxxxxxxxxxxx>
> "That's our advantage at Microsoft; we set the standards and we can
> change them."
> -- Karen Hargrove, Microsoft (quoted in Feb 1993 Unix Review editorial)
> PGP key fingerprint 85 CE 1C BA 79 8D 51 8C B9 25 FB EE E0 C3 E5 7C