computer-go: Programs learning to play Go

[Dave Dyer <ddyer@xxxxxxxxxxx>]

 My observation on NN based learning is that the few cases where
they have worked well involve situations where choosing one of a
few alternatives based on a few inputs is the mode.  The prototype
success story is Backgammon.

 Go doesn't really fit this model.  Throwing 361 inputs and outputs
at a naive network, and expecting it to learn anything, is like
throwing a pail of sand into an oven and expecting silicon chips
to emerge.  Not fucking likely.

#1: if you must try a pure learning technique, start with a reduced
domain; 3x3 or 4x4 is a good place to start.  Achieve percect play 
on 4x4, then work your way up.

#2: after you conclude that you'll never get perfect play on a 5x5
board because the domain is too complicated (my prediction), adopt
a more pragmatic approach.  Explicitly determine the fundamantals 
of the board (like group size and liberties) and concentrate your 
learning on things that actually need to be learned.

The reason Go is so intractable to simple learning paragigms 
is that many levels of abstraction are necessary to understand
a position; and there are strong interactions both within and among
abstraction layers.  Whether group A in the nothwest corner of
the board is safe depends on whether isolated stone B on the opposite
corner is 2 or 3 spaces away from stone C on the third line.  And
so on.