Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AlphaStar: Mastering the Real-Time Strategy Game StarCraft II

deepmind.com

Post reply on HN
Print view View original

51–60 of 459 posts

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

#51

Post by bduerst »

vkou wrote: post #42
bduerst wrote: post #32

Earlier quoted context omitted.

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.

Where does it say the APM spiked during battles? If it's using it head-to-head with the human player, then that's bad, but how do you know it's not just herding workers and units individually?

I get the analogy but based on the distribution, 75% of the APM for alphastar is below the mean of APM for the human during gameplay. Following that analogy, both cars are on the racetrack, except one is applying acceleration with more precision - i.e. accelerating out of a turn rather than always accelerating. Capping acceleration wouldn't matter in this case.

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

#52

Post by scarmig »

ctoth wrote: 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…

What does it matter, at this point?

The proof is in the pudding, and we are making more and more pudding everyday. Instead of caring about naysayers, we need to be working under the assumption AI is here to stay and rapidly expanding in scope, and we need to build the social and political structures to be able to handle it.

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

#53

Post by b_tterc_p »

ctoth wrote: 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…

It’s more so that the purpose of these tests is to see if the computer can strategize well. The result seems to be... not really, not yet at least.

To take a terminator situation, sure the robot will be a lot better at gun fighting, but if we can kite it with trivial attacks to make it walk into an obvious trap (not really that different from what happens in Starcraft today) then it’s not so threatening.

Nobody denies that machines are better at small tasks that are founded on reaction time, precise inputs, and wide span of attention. But the thing we’re trying to actually get them better at is strategic planning.

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

#54

Post by dilap »

ctoth wrote: 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…

It's extremely impressive, but at the same time it's still an interesting and fair question to say, "can we make an AI that beats humans while playing in a 'human like' fashion?", or alternatively, could we make an AI that would win if we put it inside a human body and made it play through those physical input restrictions?

(I do agree though that HN is way too negative overall. Partly it's just because, negative comments are more interesting. "Hey, this is cool!" doesn't have too much content. Nitpicks give you something to talk about.)

(Still, I've imagined a site where commenting is explicitly broken into two columns: Positive comments and critical comments. Then you could self-select to bask in the positivity for a bit before diving into the nitpicks.)

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

#55

Post by z_open »

kirrent wrote: post #31
z_open wrote: 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.

I'm not really sure why you think Brood War is such a pure example of basic strategy without difficult to comprehend mechanics. Even in your example, recall is far crazier in Brood War. Arbiters can also create a version of a force field on a ramp that's uncounterable and lasts far longer. They're also harder to defend against because they have so much HP.

The fact that arbiters are stronger or weaker than the equivalent abilities in SCII isn't the issue. The issue is getting the AI tech to the point where it can figure out that you have to sac a base because it will waste time sending your army there only to have them recall is going to take a lot longer. An AI can figure out that there is an arbiter on the map, and that means there is a potential for it to recall some units into your base. That's easy.

BW isn't the perfect example or pure strategy, but there are dramatically less game-changing abilities in it. Think cyclone/marauder cheeses or 2 base warp gate allins or ravagers seiging your wall. SCII in general makes attacks come quicker relative to scouting. Injects, chrono, and mules make tech and attacks come sooner compared to BW. Reliable scouting is still basically tier 2.

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

#56

Post by cm2012 »

rcheu wrote: post #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…

In the showmatched they made the computer have to look at a regular screen to control, the stalker micro was much less impressive - and mana won.

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

#57

Post by ocdtrekkie »

aerovistae wrote: post #47
shawnz wrote: post #37

Earlier quoted context omitted.

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 i…

This is why a lot of competitive games have rightly decided not to support ultrawide monitors. Being able to observe more of the game map simultaneously is a huge advantage. The only fair way to support them would be to cripple the player, by cutting off the top and bottom of the viewable range, not by extending the left and right range.

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

#58

Post by gknoy »

aerovistae wrote: post #47
shawnz wrote: post #37

Earlier quoted context omitted.

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 i…

One thing they said early on in the ~2 hour video I was watching was that, while AlphaStar had access to the full data of everything within its fog of war, it seemed to need to partition its access to it, in a way that was similar to a human checking different screens, and did so about ~30 (or was it 37?) times per minute.

This might be why changing to having to observe only one screenful at a time (rather than the zoomed out view) didn't seem to have as large an effect.

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

#59

Post by Thaxll »

rcheu wrote: post #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…

This is exactly what I think, I'd like to see how Alphastar react to "cannon rush" or other weird bo where you need to be "smart" to counter it and just not be based on insane / none human micro.

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

#60

Post by CydeWeys »

aerovistae wrote: post #47
shawnz wrote: post #37

Earlier quoted context omitted.

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 i…

This sounds like a real advantage in the AI's favor though: It can focus its attention on a lot more things simultaneously. It's not just a UI difference; the AI is actually better at this, like how a pocket calculator is actually better at division than people. This latter bit we just accept; we don't defend humans by saying the calculator is cheating because it isn't writing out the calculation by hand.

Similarly, robots are physically stronger than people at any given task you can think of. That's a real advantage of them.

Post reply on HN