[Computer-go] Mastering the Game of Go with Deep Neural Networks and Tree Search (value network)

Stefan Kaitschick skaitschick at gmail.com
Fri Feb 5 07:04:27 PST 2016


The evaluation is always at least as deep as leaves of the tree.
Still, you're right that the earlier in the game, the bigger the inherent
uncertainty.
One thing I don't understand: if the network does a thumbs up or down,
instead of answering with a probability,
what is the use of MSE? Why not just prediction rate?

On Thu, Feb 4, 2016 at 8:34 PM, Álvaro Begué <alvaro.begue at gmail.com> wrote:

> I am not sure how exactly they define MSE. If you look at the plot in
> figure 2b, the MSE at the very beginning of the game (where you can't
> possibly know anything about the result) is 0.50. That suggests it's
> something else than your [very sensible] interpretation.
>
> Álvaro.
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://computer-go.org/pipermail/computer-go/attachments/20160205/c94b3802/attachment.html>


More information about the Computer-go mailing list