Re: [Bug-gnubg] GnuBG faring poorly in backgames

[Rod Roark]

On Thursday 23 June 2005 02:00 pm, Joseph Heled wrote:
> Yes, gnubg can't learn from it's own rollouts in this case. It
> can't learn from humans since you need tens of thousands of
> examples to train a reasonable "bootstrap" NN. So the challenge is
> - find a simple enough strategy (simple enough == can be coded
> without an NN) that will play better than gnubg in those
> situations. If you think it is easy go ahead - I tried and found it
> is not so easy. when we have that we can make some progress.

Does this algorithm need to actually make plays, or is it
sufficient to provide relative values of positions?

-- Rod