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

21–30 of 459 posts

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

#21

Post by aerovistae »

Thaxll wrote: post #13

The problem is see is the AI is not better than the human, it's just 1000x faster at APM / macro. It could have a "shit" bo and still win because it's so much faster than a human. It's not really interesting tbh.

Wrong. Did you watch the presentation? Its APM was less than half that of its human opponent. If you aren't going to watch the presentation first, don't try to get involved in the discussion in such a derisive and dismissive way. "It's not really that interesting tbh"....wow. It's something that's never been algorithmically done before, no matter who tried. How can you write that off as "not interesting" as if it's totally insignificant?

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

#22

Post by z_open »

briga wrote: post #5
z_open wrote: post #2

They really should have used BroodWar for deep mind. SCII is way too volatile. Way more gimmicks available that will make it difficult for AI to come close to a human player.

Isn't the difficulty of the task the point? If it was easy it wouldn't be interesting.

What's going to be uninteresting is when their AI can never get past bronze league because the AI can't figure out that his bunker is going to get force-fielded or that observer is going to be used for a blink all-in.

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

#23

Post by jonahx »

Does anyone know if this opens the door to using these techniques for poker (given that they've now show success on games of imperfect information)?

Thus far the solutions to poker have involved solving the game tree through raw computational power and clever methods of information collapsing:

http://science.sciencemag.org/content/347/6218/145

But it seems the techniques used here might be both far more efficient, as well as able to better exploit human players (as opposed to playing a pure game theoretically optimal strategy, which is what they do now).

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

#25

Post by kirrent »

modeless wrote: post #8

AlphaStar interacted with the StarCraft game engine directly via its raw interface, meaning that it could observe the attributes of its own and its opponent’s visible units on the map directly, without having to move the camera - effectively playing with a zoomed out view of the game Additionally, and subsequent to the matches, we developed a second version of AlphaStar. Like human players, this version of AlphaStar…

The live game that was just played was against this version of AlphaStar. Mana did win, but it was by exploiting some poor defense against drops and hard countering the stalkers he knew AlphaStar favours. The AI still looked very good and the developers claimed that this version of AlphaStar wasn't significantly weaker than the versions which didn't have to use the camera.

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

#26

Post by Thaxll »

aerovistae wrote: post #21
Thaxll wrote: post #13

The problem is see is the AI is not better than the human, it's just 1000x faster at APM / macro. It could have a "shit" bo and still win because it's so much faster than a human. It's not really interesting tbh.

Wrong. Did you watch the presentation? Its APM was less than half that of its human opponent. If you aren't going to watch the presentation first, don't try to get involved in the discussion in such a derisive and dismissive way. "It's not really that interesting tbh"....wow. It's something that's never been algorithmically done before, no matter who tried. How can you write that off as "not interesting" as if it's t…

I watched it and it doesn't means anything, they said it has lower APM than a human, but what an APM means for a computer anyway? APM is just a way of mesuring how fast you click on a mice / keyboard, but the descion making is not related to the APM speed. My point is it could click 10x slower than a human and still out beat it at macro.

The real issue I have here is the game can be won by just outplaying the other at macro.

Edit:

They actually say exactly what I just said:

These results suggest that AlphaStar’s success against MaNa and TLO was in fact due to superior macro and micro-strategic decision-making, rather than superior click-rate, faster reaction times, or the raw interface.

It feels like bruteforce not really AI, that's my point.

If a computer knows everything about the game ( mvmt speed, projectile speed, ect ... ) how it is you call it smart where it's just computing power to know when to engage and when not.

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

#27

Post by AmericanBlarney »

It's certainly interesting but reminds me of DeepBlue playing Jeopardy against humans but having nd the questions fed to it electronically. Half the challenge of the game is buzzing in first. For humans, requires reading/listening and potentially making a judgement they you'll be able to answer the question and buzzing in before even hearing the whole thing. Same thing for StarCraft. If I could nap out my movers in advance and feed them to the API with precise timing, I think I could likely beat a lot of pros - all the strategies mentioned a in the article are well known. The dexterity and timing are a huge part of the challenge.

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

#28

Post by jandrese »

kirrent wrote: post #25
modeless wrote: post #8

AlphaStar interacted with the StarCraft game engine directly via its raw interface, meaning that it could observe the attributes of its own and its opponent’s visible units on the map directly, without having to move the camera - effectively playing with a zoomed out view of the game Additionally, and subsequent to the matches, we developed a second version of AlphaStar. Like human players, this version of AlphaStar…

The live game that was just played was against this version of AlphaStar. Mana did win, but it was by exploiting some poor defense against drops and hard countering the stalkers he knew AlphaStar favours. The AI still looked very good and the developers claimed that this version of AlphaStar wasn't significantly weaker than the versions which didn't have to use the camera.

You aren't kidding about the stalkers. Check out the bar chart at the bottom of the page:

https://deepmind.com/blog/alphastar-mastering-real-time-stra...

I guess it makes sense that the AI would favor such a micro-heavy unit. I imagine it would be a nightmare to deal with perfect blinking.

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

#29

Post by aerovistae »

Thaxll wrote: post #26
aerovistae wrote: post #21

Earlier quoted context omitted.

Wrong. Did you watch the presentation? Its APM was less than half that of its human opponent. If you aren't going to watch the presentation first, don't try to get involved in the discussion in such a derisive and dismissive way. "It's not really that interesting tbh"....wow. It's something that's never been algorithmically done before, no matter who tried. How can you write that off as "not interesting" as if it's t…

I watched it and it doesn't means anything, they said it has lower APM than a human, but what an APM means for a computer anyway? APM is just a way of mesuring how fast you click on a mice / keyboard, but the descion making is not related to the APM speed. My point is it could click 10x slower than a human and still out beat it at macro. The real issue I have here is the game can be won by just outplaying the other a…

....but.....but...that's EXACTLY the challenge of RTS games.....no AI has been able to beat a human at macro until now. That's the whole point...

> was in fact due to superior macro and micro-strategic decision-making

That's exactly the crux of the accomplishment! How are you writing this off as not impressive?! Like, what exactly do you want the AI to be able to do if not win by superior strategic decision-making??

> how can you call it smart when it's just computing power to know when to engage and when not.

But it ISN'T just computing power, any more than AlphaGo was. If it was, then they would have already done this years ago, wouldn't they? Anyone could just rent some servers off AWS and do it. it isn't even remotely that simple.

It's a major work of algorithmic innovation, and you don't seem to understand that.

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

#30

Post by ascar »

cellis wrote: 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 haven't played AOE for ages, but aren't the races only different in a few details like 2 units and some passive effects? In StarCraft races are vastly different.

I can't really judge AOE's complexity, but from what do you draw your conclusion? Just based on the number of rules?

Post reply on HN