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

"Ingo Althöfer" 3-Hirn-Verlag at gmx.de
Mon Feb 1 07:17:42 PST 2016


Hi Hideki,

first of all congrats to the nice performance of Zen over the weekend!

> Ingo and all,
> Why you care AlphaGo and DCNN so much?  

I can speak only for myself. DCNNs may be not only applied to
achieve better playing strength. One may use them to create
playing styles, or bots for go variants.

One of my favorites is robot frisbee go. 
http://www.althofer.de/robot-play/frisbee-robot-go.jpg
Perhaps one can teach robots with DCNN to throw the disks better.

And my expectation is: During 2016 we will see many more fantastic
applications of DCNN, not only in Go. (Olivier had made a similar
remark already.)

Ingo.

PS. Dietmar Wolz, my partner in space trajectory design, just told me
that in his company they started woth deep learning...



More information about the Computer-go mailing list