It's in the paper: "ladder capture" and "ladder escape" are features that are fed as inputs into the CNN.
Álvaro. On Wed, Jan 27, 2016 at 6:03 PM, Ryan Grant <[email protected]> wrote: > To the authors: Did the deep-NN architecture learn ladders on its own, > or was any extra ladder-evaluation code added to the playout module? > _______________________________________________ > Computer-go mailing list > [email protected] > http://computer-go.org/mailman/listinfo/computer-go >
_______________________________________________ Computer-go mailing list [email protected] http://computer-go.org/mailman/listinfo/computer-go
