Almost any game that their AI can play against itself is probably going to work. Except stuff like Pictionary where it's really important how a human, specifically, is going to interpret something.

I know a little bit about training neural networks, and I think it would be plausible to train one on a corpus of well-played StarCraft games to give it an initial sense of what it's supposed to do, and then having achieved that, let it play against itself a million times. But I don't think there's any need to let it watch how humans play. If it plays enough games against itself, it will internalize a perfectly sufficient sense of "the metagame".

If we're talking about AI in RTS games, I've always dreamed of the day when I can "give orders" in an RTS and have the units carry the orders out in a relatively common-sense way instead of needing to be micromanaged down to the level of who they're individually shooting at.