I have a few questions about the training of gnubg. Perhaps one of you can
help me out?
In reply to my mail about gnubg's poor handling of outer primes, Øystein
wrote that it was extremely hard to train those positions. Why is that?
I have read the interesting article 'the gnubg training program' on the
internet, and I know some about neural nets myself, but I still don't
understand? If the problem is in the evaluating of benchmarks because
gnubg's rollouts are biased, why not let them be rolled out by Snowie? This
seems to handle them pretty well.
My other question is about the fact that gnubg uses three different neural
nets; the crashed net, the race net and the contact net. I can see how gnubg
knows when to use the race net, but how exactly does it know when to use the
crashed net and when the contact net? I could imagine there are some
borderline positions there.