News for hackers. Stuff that matters.

Ask HN: Is it feasible to recreate Alpha Zero?

I'm looking for a toy project to learn more about AI and ML and I was thinking trying to recreate what Deepmind (following their paper) could be a good idea. Do you think it's feasible? Or what are some other good toy projects to get started?
( 1 comment | 2 points | on HN )
Re:Ask HN: Is it feasible to recreate Alpha Zero? by PaulHoule on Wednesday May 29, 2019 @06:08AM (#20038414)
You won't be able to train it as much, it won't get so good -- but you would still make a pretty mean chess engine that way.