Deep Pink: a chess engine using deep learning

Discussion of chess software programming and technical issues.

Moderators: bob, hgm, Harvey Williamson

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
nkg114mc
Posts: 63
Joined: Sat Dec 18, 2010 4:19 pm
Location: Tianjin, China

Re: Deep Pink: a chess engine using deep learning

Post by nkg114mc » Sun Mar 19, 2017 7:37 am

Hi Matthew,

Thanks for sharing the project of Giraffe! I am just trying to replicate the experiments of training a NN evaluator for Giraffe. The first few iterations running looks fine. I just need to find a faster machine for more iterations (If just using i thread, a iteration will take 23 mins on my laptop).

Besides running experiments, I am just thinking to make two minor changes on Giraffe's training setting, but not sure this has been tried by you or someone else:

1) introduce a strong opponent to play against Giraffe instead of self-playing (only the positions with Giraffe's turn will be added to the training position set);
2) play to the end of game with a result instead of playing a fixed number of moves;

I know that this has been out of the target of project that tries to learn an evaluator from just self-playing, but just curious. Not sure whether this makes sense or not. I don't know how sensitive that TD-Leaf algorithm is to the quality of games (either by self-playing or playing-against-opponent).

Post Reply