Re: [Bug-gnubg] Questions about gnubg-nn tools

[Philippe Michel]

On Thu, 5 Jan 2012, Joseph Heled wrote:

> Seems like you got a very very slightly better race net, but I would be
> surprised if it makes a difference in real life.

Ok, so a worthwhile improvement would be a decrease of at least 10% in 
benchmark error, something like that ?

> Would be much more interesting to
>  - get a better contact or crashed net
>  - expand the roll-out database for all categories (should be easy with
> the current availability of cycles)

What do you mean by roll-out database ? The benchmark data, since the 
training data seem to be 2ply evaluations ? (at least the comment in 
crashed-train-data says so). Or is it both ?

If training data is indeed 2ply evaluations, it would be relatively easy 
to use 4ply instead. And maybe rollouts for those where 2ply and 4ply (or 
3ply and 4ply) differ most, but would, say, a few hundred rollouts with 
accurate equities among hundred of thousands of evaluations be useful or 
possibly counterproductive singularities ?

> From the comments in the files, it seems you added positions in batches of 
a few thousands. You couldn't add so many specific positions, could you ? 
How were they chosen ? You start from an "interesting" one and add the 
positions after the few best moves for the 21 possible rolls for, giving, 
say, one hundred related positions, something like that ?

There are no duplicates in the training data. Isn't it a concern that the 
recurring early game positions are drowned among much less common ones ?