you are viewing a single comment's thread
view the rest of the comments
[–] 5 points 2 years ago

It worked for StarCraft. You train a model on human gameplay and then have it play the game.

https://www.theverge.com/2019/10/30/20939147/deepmind-google-alphastar-starcraft-2-research-grandmaster-level

  • source
  • parent