News for hackers. Stuff that matters.
Re:Mastering the Game of Stratego with Model-Free Multiagent... by confuseshrink on Monday July 11, 2022 @02:16PM (#32059683)
Starcraft in the form of Alphastar worked in the sense that it could beat humans, at least in the short term. The problem with the whole technique is that they had to tether it to the human examples they had gathered in the form of a divergence loss.

I haven't checked out the linked paper yet but if they managed to do something from first principles that would still be an interesting development.

There are no comments on this comment yet.