[Computer-go] Fwd: Teaching Deep Convolutional Neural Networks to Play Go
michael.markefka at gmail.com
Sun Mar 15 09:21:50 PDT 2015
I was thinking about bootstrapping possibilities, and wondered whether
it would be possible to use a shallower mimic net for positional
evaluation playouts from a specific depth on after having generated
positions with a certain branching factor that typically allows the
actual pro move to be included, hopefully finding even stronger moves,
which then are fed back as targets for the primary function/net.
Perhaps even apply different amounts of shallowness in mimic function
NN configuration as well as depth/branching for move tree generation.
No idea if there are kind of depth/branching configurations that would
make sense or seem promising, given the existing hardware options.
On Sun, Mar 15, 2015 at 2:56 AM, Hugh Perkins <hughperkins at gmail.com> wrote:
> To be honest, what I really want is for it to self-learn, like David
> Silver's TreeStrap did for chess, but on the one hand I guess I should
> start by reproducing the existent, and on the other hand if we need
> millions of moves to train the net, that's going to make for very slow
> self-play... Also, David Silver was associated with Aja Huang's
> paper, and I'm guessing therefore that it is very non-trivial to do,
> otherwise David Silver would have done it already :-)
> Computer-go mailing list
> Computer-go at computer-go.org
More information about the Computer-go