[Computer-go] PUCT formula

Gian-Carlo Pascutto gcp at sjeng.org
Fri Mar 9 10:03:32 PST 2018

On 09-03-18 18:03, Brian Sheppard via Computer-go wrote:

> I am guessing that Chenjun and Martin decided (or knew) that the AGZ
> paper was incorrect and modified the equation accordingly.

I doubt it's just the paper that was incorrect, given that the formula
has been given without log already in the original Alpha Go Lee Sedol paper.

Of course it would be funny if it was a mistake and just got copy pasted.

I never tried "fixing" the formula, I just tried the original (with
priors), and what they gave, and strength was rather similar.


More information about the Computer-go mailing list