Re:Show HN: Play Go Against a Deep Neural Network
by c-clark on Friday November 13, 2015 @05:51AM
(#10559112)
Thanks for catching that, I fixed the link.
The network itself has no capability to pass its turn, which is a consequence of the fact it was only trained to predict player moves, not passes (we thought trying to learn when to pass would be difficult and a complication best avoided). So essentially you have to play until it seems clear to you the position is won or lost. If you played on indefinitely the DCNN would start playing terrible/suicidal moves rather then passing, so you could beat in the long run.
As a very bad Go player, the bot managed to be even worse than me in several key engagements, giving me territory I had no right to capture. It still beat me by a little bit, though (I think -- the game never actually ended!) I wonder if complementing the NN with a more traditional tree search would help it play better tactically.
EDIT: Also, your paper link is broken for me: replacing https:// with http:// makes it work.