AlphaStar: Mastering the Real-Time Strategy Game StarCraft II • Hacker News Board

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

#441

Post by swaggyBoatswain » Sat, Jan 26, 2019, 2:28 PM UTC

dmoy wrote: post #192

vertline3 wrote: post #191

Earlier quoted context omitted.

Such high actions per minute does not seem fun to me, and possibly a repetitive strain injury waiting to happen.

It is why I stopped playing SC, and I was never any good anyways. Still fun, but it just hurt real bad.

I stopped playing SC competitively because it's too stressful. Both physically and mentally. Hitting 300 APM continously in a game for up to 60 minutes at a time makes your hands go numb. And the adrenaline rush makes you want to go running afterwards. With games like LoL/DoTA at least you have a chance to take a break after a gank/farming/ team wipes. With starcraft every decision has a significantly higher compounding effect

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

#442

Post by setr » Sat, Jan 26, 2019, 2:42 PM UTC

feanaro wrote: post #343

maksimum wrote: post #319

Earlier quoted context omitted.

> 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 While this would make it more fair, it would just make the micro game more similar to chess or go. I don't think humans would necessarily win in the end.

That's a good insight and yes, humans would probably be overpowered eventually. However, this is just the consequence of the fact that all games are similar if you remove external limitations such as reaction time (or, alternatively, produce a more efficient "being" which is not as subject to these limitations as some other). Starcraft is like chess in some sense. The largest fundamental difference is that it isn't a…

Tbh starcraft and dota shouldn’t really be the test games atm; turn based strategies (or rather, grand strategies) would be the far more appropriate evolution after chess and go, since we’re clearly more interested in AI macro than micro, and too much of its learning process is in trying to push the AI beyond micro-oriented thinking (probably many rounds of the AI tournament are lost simply because one AI found a new micro strategy to abuse)

But ofc, there’s no tbs or grand strategy currently out there with a real tournament scene, so you can’t really count on the devs implementing an AI-API, or even properly balanced / bug-free (far more user-testing goes into sc2/dota2 than say civ, simply by virtue of its playerbase).

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

#443

Post by dustycowboy » Sat, Jan 26, 2019, 3:20 PM UTC

wnevets wrote: post #115

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.

>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. IIRC OpenAI limits the reaction time to ~200ms when playing DoTA2. AI employing better strategies than humans will always be more interesting than AI that can out click humans.

The only way to truly have a fair fight would be to accurately model the limits of human capacities. How fast can humans move the mouse and at what accuracy? How fast can they type keyboard commands? How fast can they move their eyes? You could study those limits in a sports lab with high speed cameras, etc.

A simpler model would be to limit the bot to, say, one action per 250ms, introduce a slight delay in his reaction time, require him to move the camera to gain detailed information and take further actions, and have camera movements count as actions.

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

#444

Post by ggggtez » Sat, Jan 26, 2019, 4:16 PM UTC

There seems to be an impulse to deny the AI progress that people see in front of them. When IBM Watson won on Jeopardy, everyone claimed it was cheating because, after all, "everyone knows the answers, so Jeopardy is really only about who presses the button first". But what about the fact that a computer could know the answers at all, and so quickly? Many people didn't think it was possible, and as soon as it happens they attack the speed of the button press as if knowing the answer wasn't the hard part.

Anyone with this point of view does not seem to understand what is being shown here. This is not just "this ai beat this one player in this one match". It's an entire system of techniques for machine learning. The AI was not hard coded to learn those micro steps, like all other AIs have been. To ignore those things is to miss the point entirely.

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

#445

Post by En_gr_Student » Sat, Jan 26, 2019, 4:19 PM UTC

And now they are superhuman with regards to "Fog of war"!

A truly crushing next step would be to make "World in Flames" into a computer game, and have Alpha-Star-Zero, which is coming, to become the best it can on that.

http://www.matrixgames.com/products/296/details/World.In.Fla...

If they do that, every single military on the planet should crap themselves, including the US, Nato, Russia, China, and EU. It means that 20 years or less to robots able to operate at every level in an army from soldier to general, and able to comprehensively defeat the best humans at it, at every level. The first nation to the battlefield with this wins the world. One ironic part is that an excellent application is non-battlefield warfare. You don't have to drive a tank to conquer the world; perhaps you can buy a factory or make a deal. The corporate interface here should also be compelling.

Perhaps Alphabet will finally be able to use this to make non-advertising profits.

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

#446

Post by porpoisely » Sat, Jan 26, 2019, 4:26 PM UTC

ggggtez wrote: post #444

There seems to be an impulse to deny the AI progress that people see in front of them. When IBM Watson won on Jeopardy, everyone claimed it was cheating because, after all, "everyone knows the answers, so Jeopardy is really only about who presses the button first". But what about the fact that a computer could know the answers at all, and so quickly? Many people didn't think it was possible, and as soon as it happens…

Exactly. It's not like the AI of the past where it was essentially flowchart plus heuristics. Now, it's almost "experiential". It's tries paths and essentially sees which ones work and which don't and "learns" from it. It's similar to Dr Strange in Avengers using the Time Stone to try out possible futures to see which ones work.

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

#447

Post by bo1024 » Sat, Jan 26, 2019, 4:36 PM UTC

ggggtez wrote: post #444

There seems to be an impulse to deny the AI progress that people see in front of them. When IBM Watson won on Jeopardy, everyone claimed it was cheating because, after all, "everyone knows the answers, so Jeopardy is really only about who presses the button first". But what about the fact that a computer could know the answers at all, and so quickly? Many people didn't think it was possible, and as soon as it happens…

I see your point and partially agree. But I think part of the problem with these kinds of stunts (for lack of a better word) is it's hard to tell the difference between actual scientific advancements and benefits of throwing hundreds of years of GPU time at it.

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

#448

Post by grogers » Sat, Jan 26, 2019, 6:43 PM UTC

When deepmind announced they were working on sc2 expected it to be good, but not this good. Compare this to the top bots in SSCAIT (a BW AI tournament) and it's already so far ahead of anything that's existed up to this point. I'm eagerly looking forward to them playing all maps and matchups, I suspect it should be relatively easy to extend to. They've still got a long road ahead but this makes me think they can do it.

However, they keep harping on the APM being similar to a top human and it's just not. Maybe the average for a whole game is, but during fights it was bursting over 1500 APM with perfect execution. This wasn't just spam clicking corrosive bile or something like a human might to get that high but truly coordinated targeting and unit movement. This had lead it to use pathological unit compositions that wouldn't be effective for human play (like pure stalkers beating immortals). If they set a hard max APM to something like 600 I think it would develop more useful strategies.

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

#449

Post by derefr » Sat, Jan 26, 2019, 7:01 PM UTC

posterboy wrote: post #396

Ar-Curunir wrote: post #242

Earlier quoted context omitted.

I've read somewhere that we are basically born prematurely (as you said) because if we waited any longer then our enlarged head sizes would make delivery quite possibly fatal.

Maybe off-topic, but that's one side of the coin, and I suppose the other is that being exposed to more sensory input accelerates development, or makes it even possible (on higher levels of cognition). If this wasn't the case, why wouldn't we just be bigger and carry longer? Is size viz megafauna really that suboptimal for any more significant reasons than being hunted human hunters? I would almost say that longer pr…

> why wouldn't we just be bigger and carry longer?

The consensus in the evolutionary-anthropology community is that our hips (pelvic bones) have to be the size they are, in proportion to the rest of us, to make us able to walk upright. "Building bigger" doesn't really work, for the same reason that you can't make a giant robot—if you scale humans up, the pelvis would need to be made out of something stronger than bone to support the additional load.

The same is not as true, though, if you just make the person wider—because then you spread the same load over "more pelvis." (This is just a personal unfounded hunch of mine, but I think some human subgroups—e.g. midwestern Americans—who are at the genetic limits of baby head size, and who avoid C-sections, are currently selecting toward bigger-boned-ness.)

> I would almost say that longer pre-natal development was suboptimal, because we'd either become bored, or supersmart, but anyhow superegoistic for lack of nurture.

Keep in mind that we wouldn't be conscious for any of it. The development stage that "wakes you up" to the outside world would just occur later on, as occurs in animals with longer gestation periods (e.g. elephants, with a gestation period of 18-22 months.) This would give things like your ocular layers longer to finish developing, without really having an impact on the parts of your brain that learn stuff or think stuff.

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

#450

Post by erikpukinskis » Sat, Jan 26, 2019, 7:10 PM UTC

derefr wrote: post #146

Cookingboy wrote: post #113

Earlier quoted context omitted.

The results are obviously impressive, but even then there is a lot of work to do as far as learning efficiency goes: "The AlphaStar league was run for 14 days, using 16 TPUs for each agent. During training, each agent experienced up to 200 years of real-time StarCraft play. " MaNa probably played less than 2-3 years of Starcraft in his whole life (by that I mean 24hr x 365d x 3), and was learning with a much less foc…

Another way to think about it is that a human brain is mostly doing transfer-learning, on top of a 99%-baked deep net that was wired up during foetal development from our DNA, where that DNA-persisted model has "seen" hundreds of millions of years of training data. Humans don't have to learn to process, recognize, and classify objects in visual sense-data, for example. We can do that from the moment we're born, becau…

> Humans don't have to learn to process, recognize, and classify objects in visual sense-data

Do you have a citation for this? It doesn’t jibe with my understanding of development. For example, animals born paralyzed are blind: https://io9.gizmodo.com/the-seriously-creepy-two-kitten-expe...