Re:DARPA now has AI-controlled F-16s working as a team in vi...
by dwohnitmok on Tuesday March 23, 2021 @11:33AM
(#26556213)
As far as I understand it did actually react.
AlphaStar's training process consisted of two phases: an imitation-of-human-players learning phase that created a base set of "templates" and then self-play among agents seeded from those templates.
When creating those templates, they basically ended up with "baked-in" build orders. But self-play among agents ended up creating a variety of reactive strategies on top of those build orders, so that agents would modify them on-the-fly as the game situation changed. At a high level this is basically how humans use build orders as well.
AlphaStar's training process consisted of two phases: an imitation-of-human-players learning phase that created a base set of "templates" and then self-play among agents seeded from those templates.
When creating those templates, they basically ended up with "baked-in" build orders. But self-play among agents ended up creating a variety of reactive strategies on top of those build orders, so that agents would modify them on-the-fly as the game situation changed. At a high level this is basically how humans use build orders as well.