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

381–390 of 459 posts

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

#381

Post by sabas123 »

owens99 wrote: post #243

Interested to hear what others here think. The APM metric includes all clicks a player makes. AlphaStar's APM is lower than a typical pro's, but that does not mean it is making fewer actions. All pros try to keep a high "tempo" by constantly clicking the screen even when they are not making any actions. e.g. Instead of sending a unit to a specific location with one click, they will click 5-6 times while dragging the…

In the starcraft scene we have terms to describe what your saying: you have APM and EAPM (effective APM). Historically the fastest players were around ~230 eapm and that was considered godlike.

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

#382

Post by sabas123 »

donmatito wrote: post #368
jgrowl wrote: post #305

I wonder how useful ai will be in balancing games in the future. Games with more than one race and multiple upgrade paths seems like a nightmare to ensure that things are even for players that are equally skilled. It would be interesting to have a game that would auto-balance itself, especially if you wanted to add extra content without having to worry about throwing everything off.

Total War Warhammer is a very interesting case for that. Many, many races, units, items etc. Much more than Starcraft. And yet the balancing seems quite good! There are obviously tier1, tier2, tier3 races, but even these tiers are disputed and tier1 races rarely win tournaments

I would argue that without a proper competitive scene (which Total War Warhammer does not have) it is impossible to measure if it is actually balanced or not.

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

#383

Post by yaps8 »

sleepydog wrote: post #63
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…

I'm curious, would the AI be able to see cloaked units? In sc1 you could see them,( I think sc2 is the same) but it was very difficult. How does the 'raw' interface expose that subtlety?

Not sure but I think in the video they say the AI does not see cloaked units.

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

#384

Post by fernandotakai »

gpm wrote: post #372
bitxbitxbitcoin wrote: post #281

Earlier quoted context omitted.

Was Starcraft the only/main game that you played?

Yes, basically the only for several years at that point. A few hours here and their of other games but nothing at all substantial.

i already had some RSI, but playing SC2 made it a lot worse (i stopped playing when i got to plat as a zerg because it required enough APM to hurt)

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

#385

Post by posterboy »

saberience wrote: post #207
dcl wrote: post #164

Earlier quoted context omitted.

This is a widely underappreciated fact when it comes to comes to comparing the 'training experience' of humans versus bots. And it extends far beyond processing 'sense data' - A human likely has some level of understanding of how the game works based on experience from other games it has played and from 'real life' - we know almost instinctively that 'high ground' is likely to give a combat advantage without having t…

All of our knowledge of how to play games and so on has come from our current lifetime. We do not have a "genetic memory" that means we have learnings from cavemen or some other such nonsense. Our DNA contains instructions on how to grow a human, it's not a mega hard drive with millions of years of collective memory. If a 19 year old is good at Starcraft, he's good at Starcraft because he spent two or three years pla…

The GP is underselling the fact that in the human years of being a pro player they think through many more games and may even dream of it. I certainly went to bed after a lengthy session with images of the game still in front of me. Although that might be more about micro, the macro skills are somewhat transferable from other "games". RTS simulate economy, amongst other things, after all.

GP's claim, "99%-baked deep net that was wired up during foetal development from our DNA" is also unfounded, if not completely overblown. I am far from a student of biology, much less an expert, but intelligence is still seen as an emergent property. The real kicker might be that organizing thoughts might be a "game" of it self, that is learned in development and constantly exercised. Talk about self-play.

I recently read a similar question about "inherent mathematical language", ie. capability, and the given opinion was that there is no consensus, except perhaps for basic addition, which I guess concerns vision, ie. seeing a set of things and knowing the count is +++++. That works only up to around +++++++ items at best, according to findings.

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

#386

Post by fernandotakai »

Narishma wrote: post #295
tux1968 wrote: post #282

Earlier quoted context omitted.

The APM of AlphaStar was about half of the professional player in this match. Check out: https://youtu.be/cUTMhmVh1qs?t=3189

But when it counts, such as during micro-heavy battles, it's much faster and more precise than a human.

yup. you could have 200 apm, but as long as your clicks and button presses are perfect, you are going to win against someone with 800 but is super imprecise.

blink stalkers are basically perfect for an AI because of the precision they can blink them around.

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

#387

Post by fernandotakai »

nopinsight wrote: post #296

Fun observation on the possible reason why they chose Protoss from the publicity standpoint: Zerg — Too icky for some in the general public Terran — Too human-like. Might clearly trigger the imagery of human-robot wars.

imho, the AI had a better time playing as a Protoss because of blink stalkers.

you can probably perfectly micro marines + marauders + medvacs with stim, but it's a lot harder than blink.

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

#388

Post by taneq »

celeritascelery wrote: post #228
bsaul wrote: post #204

Earlier quoted context omitted.

You seem to forget the way it learned to play every part of the game (not just micro fights). That is, not by having any developer code any rules, but simply by "looking" and "playing". That's the great accomplishment and nothing like that could have been done 10 years ago.

What makes this interesting is if they can make a computer program better at Starcraft strategy then a human. How they did that is irrelevant. If having developers code rules makes a better AI then deep learning, then the former is the most impressive solution. What they did is a great accomplishment and the AI they created was amazing, but I feel like the faster-then-humanly-possible micro makes any accomplishment h…

> How they did that is irrelevant.

Emphatically not.

If they beat human performance in this (non-AI-building) field by humans painstakingly coding rules for specific situations, then that's cool I guess but not groundbreaking, because the solution doesn't generalise.

If they beat human performance in a field heretofore intractable by software by throwing the basic rules and a ton of compute at an algorithm and then waiting for six weeks while the algorithm figures the rest out by itself, then that absolutely is qualitatively different.

The reason being, of course, that if they can find an algorithm that works like this across a wide enough problem space then eventually they'll find an algorithm which will work on the question of "build a better algorithm." After which, as we know, all bets are off.

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

#389

Post by posterboy »

pesmhey wrote: post #201
gamegoblin wrote: post #67

Earlier quoted context omitted.

In the mass stalker battles, the AI APM exceeded 1000 a few times, and no doubt that most of that was precisely targeted. Whereas a human doing 500 APM micro is obviously going to be far more imprecise. I think a far more interesting limitation would be to cap APM at 150 or so, or to artificially limit action precision with some sort of virtual mouse that reduced accuracy as APM increased.

There would be an entire new dimension of decision making, in addition to good macro, where you have to prioritize actions. Will be interesting to see.

I said so before, but is it really a big difference from controlling a unit that can also only do one thing at a time? The agent controls itself just like another unit, with a constraint on APM available to control other units. On the one hand, these APMs add a new parameter, if the constraint is implemented naively. On the other hand, if there are viable strategies against ultrahigh APM opponents, then the constrained is really rather limiting the dimensions of the decision space and to good effect, finding viable strategies that take less effort. Hence such things are called "hyperparameters" (I think that's something different, but you know what I mean). Likewise, the game isn't as fast as to need 100 screen switches per second, if good planning allows batching and bursting actions.

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

#390

Post by dwighttk »

NicoJuicy wrote: post #320
confiscate wrote: post #275

Earlier quoted context omitted.

Yes I am curious of this too. What happens if the human has a giant TV screen that can see the whole map at once Or, what if we slow down the game, so that the human can actually pause the game each second and consider what to do next. That's basically what the computer is allowed to do

It would massively be faster I think. Upgrade building 3 comes available when you have enough resources. A separate tab with insufficient resources gives you an overview with what you need to finish a,b,c. A red alert appears when an enemy is spotted. You can click nearby units attack or a FSM with the attack strategy. An finished building automatically will be placed near the town center. Not working farmers can sea…

Stalker unit AI could be microing perfectly for you...
Post reply on HN