[Computer-go] mini-max with Policy and Value network

"Ingo Althöfer" 3-Hirn-Verlag at gmx.de
Tue May 23 20:33:34 PDT 2017


Hi, just my 2 Cent.

"Gian-Carlo Pascutto" <gcp at sjeng.org> wrote:

 
> In the attached SGF, AlphaGo played P10, which was considered a very
> surprising move by all commentators...
> I can sort-of confirm this:
> 
> 0.295057654 (E13)
> ...(60 more moves follow)...
> 0.000011952 (P10)
> 
> So, 0.001% probability. Demis commented that Lee Sedol's winning move in
> game 4 was a one in 10 000 move. This is a 1 in 100 000 move.

In Summer 2016 I checked the games of AlphaGo vs Lee Sedol
with repeated runs of CrazyStone DL:
In 3 of 20 runs the program selected P10. It
turned out that a rather early "switch" in the search was
necessary to arrive at P10. But if CS did that it
remained with this candidate.

Ingo.


More information about the Computer-go mailing list