Anyone knows a resources (papers, articles and especially repositories) regarding controlling multiple units with RL.
The controlled units should not be fixed, for example in Real Time Strategy the agent builds various units (workers, soldiers ...) and later controls them. During the game various units could die and new ones are built.
I think good contemporary example is AlphaStar, while OpenAI Five controls just a single agent. This might be incorrect since I've never played those games.