[king-rat]

Not being robust to strategies it hasn't seen before is a serious shortcoming in a real time strategy game. That also indicates an interesting flaw in how this model is trained - in the millions of games it plays against itself, how do you ensure that it tries every viable (and some inviable) strategies? Sure, it couldn't best Serral but I wonder how it would fare against Has, a player known for some pretty off the wall builds.

[jplayer01]

> Not being robust to strategies it hasn't seen before is a serious shortcoming in a real time strategy game.

I'm not sure if you've actually played or followed competitive SC2. This is absolutely normal. Players will pull something completely unexpected out of a hat and win. The losing player will learn from it in future games. That's just how it goes. Unexpected strategies are really hard to counter when you've never seen them before, and they're often employed to directly counter what you're doing right then and there. So you've been countered and dealt a devastating blow, which means figuring out how to come back from that can be hard to impossible. It's a thoroughly human failing in every way. I'd be more concerned if the AI wasn't able to learn to counter it in future matches.

[Nimitz14]

I don't think you understood his point. A player doesn't need to have seen a strategy before to react correctly to it. Sometimes a player will pull something completely unexpected out of a hat and lose, because the other guy reacted correctly thanks to his game experience. If you watch any high GM player stream half the time his reaction to what his (worse) opponent is doing is "WTF is this?" as he then proceeds to crush it. Alphastar cannot do that.

[jplayer01]

I do understand his point. There are just as many examples of people being so overwhelmed by the new strategy that they don't know how to respond to it and lose. And then learn how to deal with it in later matches. Also, downvoting me for disagreeing is a dick move.

[TaupeRanger]

And yet, in Go, the AI adapted to any "weird strategy" and won regardless. The fact that AlphaStar can't is an obvious weakness.

[empath75]

I would say it’s a weakness but I think it’s shared by most players. A ‘weird’ go strategy isn’t going to involve new kinds of pieces on the board or someone developing a win condition at a place on the board you can’t see.

You can lose a Starcraft game easily if someone is doing something novel and you don’t happen to scout the right place on the board soon enough.

[king-rat]

I do actually follow competitive SC2. My point is that for DeepMind to master this game in the same way it has with Go and chess, it must be able to anticipate counter plays ad infinitum. Otherwise humans will continue to beat it.

[chillacy]

Are new strategies more important in SC2 than go/chess? From the blog it seems like the AI learns from self-play so if it doesn't come up with a strategy, it won't know how to counter it. But that seems like it should apply to chess and go as well.