Thanks for the explanation. I agree that there is no actual consistency in
exploration terms across historical papers.
I confirmed that the PUCT formulas across the AG, AGZ, and AZ papers are all
consistent. That is unlikely to be an error. So now I am wondering whether the
faster decay is
I talked to Chenjun just now so this is what we both remember.
The PUCB formula as published in Chris Rosin’s paper actually has an additive
knowledge term, and it looks nothing like the two different PUCT variants tried
in AlphaGo and our paper.
Chenjun tried an additive term as in Chris’
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
However, the formula in the AGZ paper doesn't look like any "UCT variant".
Formula from paper: Cpuct * P(s,a) * sqrt(Sum(N(s,b))) / (1 + N(s,a)) Note that
there is no logarithmic term, and the division by N+1 falls outside the sqrt.
For comparison, a normal UCT term looks like
Hi,
Generating self-play games represents smost of the computation burden in LZ
project. With current setting, games are generated with a 1000 nodes/move
budget. As a rough guide, considering 250 moves game length and ignoring resign
and possible tree reuse, I assume generating a game,
On 08-03-18 18:47, Brian Sheppard via Computer-go wrote:
> I recall that someone investigated this question, but I don’t recall the
> result. What is the formula that AGZ actually uses?
The one mentioned in their paper, I assume.
I investigated both that and the original from the referenced
