[Computer-go] Converging to 57%
brian.kihoon.lee at gmail.com
Tue Aug 23 07:00:19 PDT 2016
I've been working on my own AlphaGo replication (code on github
https://github.com/brilee/MuGo), and I've found it reasonably easy to hit
45% prediction rate with basic features (stone locations, liberty counts,
and turns since last move), and a relatively small network (6 intermediate
layers, 32 filters in each layer), using Adam / 10e-4 learning rate. This
took ~2 hours on a GTX 960.
As others have mentioned, learning shoots up sharply at the start, and
there is an extremely slow but steady improvement over time. So I'll
experiment with fleshing out more features, increasing size of network, and
longer training periods.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Computer-go