[Computer-go] Board evaluation using a convolutional neural network
michael.sue at gmx.de
Fri Jan 15 13:26:27 PST 2016
> My experience is the same: My CNN was a very poor judge of life and
> death. Part of the problem is that I couldn't get Pachi to behave
> exactly the way I wanted (play to maximize score; play to the bitter
> end, assuming everything left after two passes is considered alive). But
> perhaps there is some deeper problem, or we are just missing an
> important twist to make the technique work.
I think the problem with live and death is that if it comes to a group
that will die the pro will resign; if he can save the group the bot may
not even got it that there might have been a live and death issue.
So, why can't you train the DNN on pure live and death problems, just
like human players do it - from time to time. There are many collections
(some even with solutions).
More information about the Computer-go