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.
It could become better than people at playing Pictionary, by drawing images that are most likely to be correctly recognized rather than the human way of translating the model in its head into a picture, and by analyzing what models are most likely to produce a picture rather than the human way of translating the picture into a model in its head. Except if you mean that it playing against itself would make it diverge into its own language of pictures.
Although it might optimize in a direction that doesn’t follow the spirit of the game, anologous to writing out the name of its task.
Actually that could be interesting—could it invent a language that is maximally efficient at communicating concepts?
To your last one, you might enjoy a MOBA where individual players have only information about stuff in their line of sight, but there’s an extra player whose job it is to see everything and give “orders”. I think there was one like that...
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.
It could become better than people at playing Pictionary, by drawing images that are most likely to be correctly recognized rather than the human way of translating the model in its head into a picture, and by analyzing what models are most likely to produce a picture rather than the human way of translating the picture into a model in its head. Except if you mean that it playing against itself would make it diverge into its own language of pictures.
Although it might optimize in a direction that doesn’t follow the spirit of the game, anologous to writing out the name of its task.
Actually that could be interesting—could it invent a language that is maximally efficient at communicating concepts?
To your last one, you might enjoy a MOBA where individual players have only information about stuff in their line of sight, but there’s an extra player whose job it is to see everything and give “orders”. I think there was one like that...
Demis Hassabis mentioned StarCraft as something they might want to do next. Video.