Settings

Theme

Keras Implementation of Alpha Zero for Chess

github.com

78 points by atroyn 8 years ago · 4 comments

Reader

bradknowles 8 years ago

In the repo, they suggest that you instead go support another project. Namely, https://github.com/glinscott/leela-chess

  • waterhouse 8 years ago

    Oh man, it's like BOINC. (In fact, perhaps one could incorporate it into BOINC.) I wonder if, after a while, the most powerful ML platforms in the world will be volunteer-run distributed systems. That would be an interesting situation.

thope 8 years ago

If anybody is interested, you will find ~300 millions PGN to train your NN models on chess games here : https://database.lichess.org/

  • atroynOP 8 years ago

    One interesting thing about the 'zero' approach is that it learns through self-play. So you can use a database to bootstrap the learning, but in principle you'd only need the game rules and enough training time.

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection