[Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

Gian-Carlo Pascutto gcp at sjeng.org
Thu Oct 26 11:02:53 PDT 2017


On 26-10-17 15:55, Roel van Engelen wrote:
> @Gian-Carlo Pascutto
> 
> Since training uses a ridiculous amount of computing power i wonder
> if it would be useful to make certain changes for future research,
> like training the value head with multiple komi values
> <https://arxiv.org/pdf/1705.10701.pdf>

Given that the game data will be available, it will be trivial for
anyone to train a different network architecture on the result and see
if they get better results, or a program that handles multiple komi
values, etc.

The problem is getting the *data*, not the training.

-- 
GCP


More information about the Computer-go mailing list