Re: computer-go: Learning from existing games

[Erik van der Werf <E.vanderWerf@xxxxxxxxxxxxx>]

Markus Enzenberger wrote:
> The big problem is the training time. I found TD with self-played games
> superior to other training methods and it takes at least 100000 games
> for best results (several weeks or even months on a fast PC).
> Algorithms for faster weight update are not necessarily helpful, because
> they decrease the exploration that is done with a given set of weights.

Do you train on-line or in batch style (e.g., several games before a
weight update)?

I think algorithms for faster weight update only work well with stable
gradient information. On-line learning may not provide good enough
gradient information.

Erik.