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

31–40 of 459 posts

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

#31

Post by kirrent »

z_open wrote: post #19
kirrent wrote: post #15

Earlier quoted context omitted.

As much as I love brood war, great micro over a large number of units with wide awareness (things which appear to be easy to AlphaStar) would be ridiculously overpowered, even with completely average strategy. Brood War is an awesome game because it's constantly asking too much of its players at all times. I can't imagine games against an AI which has far more attention and micro to give would be too interesting.

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.

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

#32

Post by bduerst »

z_open wrote: post #19
kirrent wrote: post #15

Earlier quoted context omitted.

As much as I love brood war, great micro over a large number of units with wide awareness (things which appear to be easy to AlphaStar) would be ridiculously overpowered, even with completely average strategy. Brood War is an awesome game because it's constantly asking too much of its players at all times. I can't imagine games against an AI which has far more attention and micro to give would be too interesting.

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-mastering-real-time-stra...

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

#33

Post by samstave »

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…

{{Delivered in the voice of the female British lady who would narrate Beyond 2000 series of shows - or the Modern Marvels narrator, to your mental predilection}}

After just decades in development, it is clear that the endeavors of those research scientist have finally bore fruit. And today its in the form of:

Intent based modeling, augmented with AI, which provides the reality we see today in both gaming and weapons systems.

The user, who must be human, is provided a range of inputs based on the desired outcome of the interaction with the systems and the real world.

What results, is truly remarkable.

A human is capable of multi-dimensional abstract thought, in a way that a computer cannot. As such - their intent is wired over to a swarm of objects with the most amazing capabilities.

A user can direct a swarm of either virtual bots or physical drones to accomplish a task. She can also combine the efforts of both physical and virtual for even greater effect.

Here we see a swarm of bots who are thwarted by a physical barrier.

The human driver can then instruct his virtual AI bots to attack the security system of the building to allow his drones to have passage.

But she does this through merely the intent for the portal to be open. The bots do the rest.

All the while the user is updated with real-time information on how the operation is progressing.

So, in the future, you may soon see just such technology applied to your kitchen or living room, where bots will cater to your every waking need - and sometimes your non-waking needs as well.

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

#34

Post by saberience »

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…

Its APM maxed out at 1500apm which is far more than any normal human.

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

#35

Post by cellis »

ascar wrote: post #30
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?

Each civ (race) has about 2 different bonuses (e.g. Indian villagers work faster) and in addition a unique unit. Competitive players now play with about 20 civs. Each civ also has a "team bonus" (e.g. Teams with a Spanish player get 33% more gold per trade trip, teams with a Persian player get upgraded buildings ). In addition to that, each civ has a different tech tree, as well as starting resources or -- in rare cases -- starting units.

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

#36

Post by dfan »

kingbirdy wrote: post #24

Very exciting results. However, I'm a bit confused by this graph [0], could anyone explain how I'm supposed to interpret it? 0: https://deepmind.com/blog/alphastar-mastering-real-time-stra...

I was confused too; it has a weird format that I think hurts comprehension rather than aids it by making you think you're not looking straight at the data.

Ignore the fact that the "Training Days" axis is drawn diagonally. The system is creating about 40 agents per day; by the end of day 14 it's made 610 or so. The graph shows, for any given time of training (vertical axis, going down), what is the distribution of trained agents that it's chosen in order to be unexploitable (you wouldn't want to choose rock all the time in rock-paper-scissors, for example). So, for example, at the end of day 14, it's using a selection of agents with numbers 595 through 610 or so, which means they've all been created within the last day.

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

#37

Post by shawnz »

aerovistae wrote: post #12
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…

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

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

#38

Post by aerovistae »

saberience wrote: post #34
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…

Its APM maxed out at 1500apm which is far more than any normal human.

That's instantaneous APM, not general APM over the course of the game. The human player's instantaneous APM went well past 1000 at certain moments during the course of the matches, too. All that means is a few clicks as fast as possible.

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

#39

Post by Quekid5 »

z_open wrote: post #19
kirrent wrote: post #15

Earlier quoted context omitted.

As much as I love brood war, great micro over a large number of units with wide awareness (things which appear to be easy to AlphaStar) would be ridiculously overpowered, even with completely average strategy. Brood War is an awesome game because it's constantly asking too much of its players at all times. I can't imagine games against an AI which has far more attention and micro to give would be too interesting.

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 could micro against MaNa's army on 3 fronts in game 4 and how it was able to basically perfectly drain the Immortal barriers in the game where MaNa actually should have been able to defend against a human mass stalker build ~100% of the time.)

One thing they weren't clear on was how it could tell how much health, etc. each enemy unit had -- did it have to spend an "action" (like a player would have to click) to do that? If so, then that's even more insane in terms of micro ability.

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.

[1] This was not the case for the final game which it lost.

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

#40

Post by tanilama »

aerovistae wrote: post #12
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…

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.

Actually, I would say this might be the strength of AI from another perspective: the ability to observe and monitor global information without losing attention. Or in other words, attend to the whole picture from get go without being overwhelmed.

While it is an unfair advantage in competitive gaming, but in more realistic settings, there is no requirement that AI needs to have only 2 eyes. It can have as many as it could handle, while human can't scale the same way.

Post reply on HN