I was able to replicate the success (and with more iterations,
failure) of the all-as-first heuristic.  But I have not been able to
see an improvement when I prohibit multi-stone suicides (I always
prohibit single-stone suicides).  Forgive me, but I am only interested
in your response if you have actually tried allowing multi-stone
suicides while preventing single-stone suicides in your engine,
because feelings and intuition don't trump what I have witnessed in my
two independent engines.

Also, I have been unable to reproduce the benefit of the proximity
heuristic (play adjacent or diagonal to the last move 25% of the time)
in the one engine that I have tried it.  Has anyone besides Peter
Drake (it was his paper, right?) reproduced this benefit?
_______________________________________________
computer-go mailing list
[email protected]
http://www.computer-go.org/mailman/listinfo/computer-go/

Reply via email to