Live data from Hacker News

AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

deepmind.com

41–50 of 459 posts

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#41
Every year or so we get another huge advance... Well, more accurately, something comes along to benchmark the state of AI research against a human activity.

Then come the HN comments.

For Alpha Go:

Oh this is impressive but can't generalize. Wake me up when it doesn't have to have information precoded/doesn't learn from human players

For alpha go 0:

So this is cool but not amazing because they're all perfect information games.

And now here we have this, and people who haven't even watched the presentation are yammering about stuff like the APM, or how this isn't impressive because of ... Well, something?

If I believed in a terminator scenario, I would point out that a robot, too, will presumably have higher APM than all of us desk warriors.

It really feels like there are just some people who are religiously attached to being the only known intelligent entities on the planet, to the point where, when presented with evidence that hey, this is actually a thing, they will stick their fingers in their ears and shout about how unreal/unfair it all is.

I invite you to have a look back at the other announcement threads from Deepmind and OpenAI. I decided not to directly quote people as I don't want this to get personal, but I couldn't just sit here and watch the same old story play out again without at least mentioning that these same people have been wrong, and wrong, and wrong, and will presumably continue to be wrong.

Exponential curves are unintuitive.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#42
post #32
post #19

Earlier quoted context omitted.

They are planning on limiting the APM of the AI anyway. With BW, you can focus on an AI learning basic strategy with incomplete information. With SC2, you mix in a hole assortment of figuring out how crazy abilities like force fields and recall. It's going to take much longer for an AI to anticipate when its opponent is going to force field the ramp and warp into the main.

Are you so sure? APM limits on the AI aren't necessary, which is a real insight FTA: >In its games against TLO and MaNa, AlphaStar had an average APM of around 280, significantly lower than the professional players, although its actions may be more precise. This lower APM is, in part, because AlphaStar starts its training using replays and thus mimics the way humans play the game. https://deepmind.com/blog/alphastar-…

AlphaStar had an average APM of 280, but during battles, it's APM would spike up to ~1500.

It's like saying that my car has an average speed of 2mph. Sure, it does - but that's because it spends 23 hours a day sitting in a garage.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#44
post #41

Every year or so we get another huge advance... Well, more accurately, something comes along to benchmark the state of AI research against a human activity. Then come the HN comments. For Alpha Go: Oh this is impressive but can't generalize. Wake me up when it doesn't have to have information precoded/doesn't learn from human players For alpha go 0: So this is cool but not amazing because they're all perfect informat…

I've heard what you said more pithily put as "true AI is anything we can't make a computer do right now".

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#46
This is really impressive, I didn't expect starcraft to be played this well by a machine learning based AI. I'm excited to read the paper when it comes out!

That said, I'm not sure I agree that it was winning mainly due to better decision making. For context, I've been ranked in the top 0.1% of players and beaten pros in Starcraft 2, and also work as a machine learning engineer.

The stalker micro in particular looked to be above what's physically possible, especially in the game against Mana where they were fighting in many places at once on the map. Human players have attempted the mass stalker strategy against immortals before, but haven't been able to make it work. The decisions in these fights aren't "interesting"--human players know what they're supposed to do, but can't physically make the actions to do it.

While they have similar APM to SC2 pros, it's probably far more efficient and accurate so I don't think that alone is enough. For example, human players have difficulty macroing while they attack because it takes valuable time to switch context, but the AI didn't appear to suffer from that and was extremely aggressive in many games.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#47
post #37

Earlier quoted context omitted.

yeah I was disappointed to discover it worked this way. don't get me wrong, it's a major accomplishment in AI regardless, but it's a significant advantage and it would be easier for me to appreciate the AI's skill if I didn't have to keep reminding myself that it can see the whole map at once. it's such an information advantage.

It sounds to me like, although it could see the whole map at once, the fog of war was still applied. So the bot really just got as much information as the minimap would normally give a human player. > it could observe the attributes of its own and its opponent’s _visible units_ on the map directly

No, not true. Just had an extended argument with a friend over this. Here are some of my arguments against what you're saying:

1. While it's true that a human player could see everything the AI is seeing, the human player has to spend time and clicks to go see those things, whereas the AI sees it all simultaneously without having to use any actions or spend any time to take it in.

2. Emphasis on the computer seeing it all simultaneously. The computer can see the state of two health bars on opposite sides of the map at the same time, or 100 healthbars in a hundred places at a time. A human cannot do that, and even trying to move the view around fast enough to do so would render it impossible to actually do anything else.

3. If it's true that seeing more at once is not advantageous, then it must also be true that seeing less at once is not disadvantageous. So by that reasoning a player playing on a 1 inch x 1 inch screen would not have any disadvantage, since after all they're getting just the same amount of information as long as they move the screen around enough! Reducto ad absurdum, a player with a 1 pixel x 1 pixel screen has no disadvantage either, because they have access to the same information as long as they move around quick enough. It quickly becomes evident that smaller screens inhibit your knowledge of the game state, and therefore larger screen benefit your knowledge of the game state.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#48
post #9

I would really like to see this for Age of Empires II. I think AOE has far more races and is a far more complex game ( although I'm biased because I haven't played SC2 as much as AOEII ).

I have played both games and a fan of both. Starcraft is definitely more complex than AoE for AI development and that's why the researchers must have chosen it. The complexity of AI depends on how many potential decisions you can make at any point of time. Here are a few reasons why: 1) Starcraft races have completely different build trees and different advantages. This has a large cascading effect of early decisions in the game. 2) Starcraft has much more micro potential that AOE. There are many units with sort of super powers like Stalkers can teleport and infestors can take control of enemy units. In AOE, you can only issue attack commands to most units. 3) Variety of units. Since Starcraft also has air units which may or may not be able to attack ground units, you have more options within a race to create a unique army/air force combination. 4) The Starcraft map terrain is hierarchical whereas AOE happens on a flat map. There are interesting locations on the map where a smaller army may be able to defeat a larger army based on positioning.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#49
post #39
post #19

Earlier quoted context omitted.

They are planning on limiting the APM of the AI anyway. With BW, you can focus on an AI learning basic strategy with incomplete information. With SC2, you mix in a hole assortment of figuring out how crazy abilities like force fields and recall. It's going to take much longer for an AI to anticipate when its opponent is going to force field the ramp and warp into the main.

> They are planning on limiting the APM of the AI anyway. They did that in these games. (Or at least, it didn't abuse absurdly high APM.) It still had insane micro a) because it had a FoV which basically extended to the combined FoV of all if its units[1] rather than having to move a screen-size FoV, and b) when it micros it never really "misclicks" like a human would do under pressure. (This was most obvious in how…

>It still had insane micro a) because it had a FoV which basically extended to the combined FoV of all if its units[1] rather than having to move a screen-size FoV, and b) when it micros it never really "misclicks" like a human would do under pressure.

This is an oversight that I imagine they will eventually fix as well. Doesn't make sense to allow the AI to do this, because the focus is on the AI understanding the game.

>Anyway, disagree about BW. Perfect micro in BW is possibly even more devastating than in SC2, IMO, because there are all these weird glitches that you can do -- the best players can do them some of the time, but no players can do it perfectly all of the time.

I didn't mention micro specifically, I mentioned abilities. The perfect micro issue can again be solved by limiting the AI's APM. They may be able to execute micro tricks, but not constantly.

Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

#50

I didn't catch if they mentioned this in the interview, but what would have happened if they let AlphaStar play against other races, not Protoss only, would it be completely lost, unable to achieve anything?

The current version would flounder because it has never seen the other races. But that is not a fundamental limitation. All it would take to fix it is more training time.
Post reply on HN