[Computer-go] Move evalution by expected value, as product of expected winrate and expected points?
jasiek at snafu.de
Tue Feb 23 03:54:22 PST 2016
On 23.02.2016 11:36, Michael Markefka wrote:
> whether one could train a DCNN for expected territory
First, some definition of territory must be chosen or stated. Second,
you must decide if territory according to this definition can be
determined by a neural net meaningfully at all. Third, if yes, do it.
Note that there are very different definitions of territory. The most
suitable definition for positional judgement (see Positional Judgement 1
- Territory) is sophisticated and requires a combination of expert rules
(specifying for what to detemine, and how to read to determine it) and
A weak definition could predict whether a particular intersections will
be territory in the game end's scoring position. Such can be fast for MC
or NN, and maybe such is good enough as a very rough approximation for
programs. For humans, such is very bad because it neglects different
degrees of safety of (potential) territory and the strategic concepts of
sacrifice and exchange.
I have also suggested other definitions, but IMO they are less
attractive for NN.
More information about the Computer-go