DARPA now has AI-controlled F-16s working as a team in virtual dogfights

Re:DARPA now has AI-controlled F-16s working as a team in vi... by tornato7 on Tuesday March 23, 2021 @03:53AM (#26552233)

As an avid StarCraft player I still think AlphaStar is one of the most impressive AI programs ever made. While it didn't get everything quite right, it exhibited planning and creativity in it's builds, and didn't just do the same exact thing every time; it scouted and reacted to the opponent's moves with professional-level proficiency.

[ Parent | on HN ]

Re:DARPA now has AI-controlled F-16s working as a team in vi... by CyanBird on Tuesday March 23, 2021 @04:25AM (#26552437)

It didn't react it had pre-planned build orders

That's something which was mentioned when it came to deep mind team talking of all the "different agents" they had trained

[ Parent | on HN ]

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.

[ Parent | on HN ]