News for hackers. Stuff that matters.

A comment on Grandmaster level in StarCraft II using multi-agent reinforcement learning. Parent comment

Re:Grandmaster level in StarCraft II using multi-agent reinf... by anonymfus on Thursday October 31, 2019 @12:37PM (#21410660)
May be make self-play asymmetrical so sides in the game would have different sets of limitations? So main agent would have subhuman micro and exploiter agents would have superhuman micro.
[ Parent | on HN ]

There are no comments on this comment yet.