[computer-go] Computer go in 7x7

Don Dailey drd at mit.edu
Thu Oct 12 12:04:52 PDT 2006


On Thu, 2006-10-12 at 11:51 -0700, Christoph Birk wrote:
> > The current result is 52.5 percent for white.   Of course if the
> > programs were playing perfectly it should be zero percent for white
> > if 9 is the correct komi.
> 
> Why are you not using komi=9 ?

Because Lazarus can't handle integer komi.   It has to be 8.5 or 9.5.

I could make some minor modifications to make it work with an even komi
if I wanted to,  but I didn't want to hack code for this experiment.

Besides,  if it thinks WHITE wins at 8.5 komi,  it will think white wins
even more at 9.0 komi so I know what I wanted to find out.

My next test would likely be to change it to 7.5  to find out if this is
seen as a black advantage.  


- Don





> Christoph
> 



More information about the computer-go mailing list