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

61–70 of 459 posts

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

#61

Post by b_tterc_p »

aerovistae wrote: post #29
Thaxll wrote: post #26

Earlier quoted context omitted.

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??…

GP has it backwards. The Ai won on micro, not macro.

Computer apm is not the same as human apm. Humans have numerous unnecessary actions, whereas computers don’t. This is visible just watching the game. Computer dominated on micro.

When the computer lost, it was because it failed to cope with a basic macro curveball

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

#63

Post by sleepydog »

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?

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

#64

Post by hughzhang »

This is really impressive. Even though the camera hack / uncapped APM limits (only the average was capped) made this version slightly unfair since the ability of an AI to micro insanely well with stalkers is basically unbeatable, I feel confident based on this performance that Deepmind will release a superhuman AI with lower EPM than humans very soon from now.

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

#65

Post by hughzhang »

jandrese wrote: post #28
kirrent wrote: post #25

Earlier quoted context omitted.

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.

Dealing with perfect blinking is basically impossible, since you can blink back your units right before they die. Stalkers are balanced around the fact that HUMANS have limits to how well they can micro.

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

#66

Post by hughzhang »

tanilama wrote: post #40
aerovistae wrote: post #12

Earlier quoted context omitted.

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 c…

While that would be amazing if true, I'm pretty sure if you take away the stalker blink micro AlphaStar loses hands down to humans. This isn't taking away from Deepmind's victory at all, but I think micro was what made the AI come out ahead in this one. In many of the games, Mana had much better macro only to lose to blink stalkers.

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

#67

Post by gamegoblin »

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 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.

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

#68

Post by saberience »

aerovistae wrote: post #38
saberience wrote: post #34

Earlier quoted context omitted.

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.

You can't compare the two. No human can do 1000 meaningful actions per-minute. Even when a human is doing 400apm, probably 100 of those are meaningless spam clicks. All of AlphaStar's actions are meaningful actions.

So when AlphaStar is doing 1000-1500 APM, there's no way a human could do that or compete with that. This doesn't impress me because it's obvious if you create something that can do something way faster than a human it will win.

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

#69

Post by b_tterc_p »

jonahx wrote: post #23

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…

Probably not. The AI demonstrated today was shown to be exploited with a strategy that wasn’t especially devious. It’s good at core mechanics but not strategically clever. I would bet on the optimal strategy over this one.

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

#70

Post by gamegoblin »

hughzhang wrote: post #65
jandrese wrote: post #28

Earlier quoted context omitted.

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.

Dealing with perfect blinking is basically impossible, since you can blink back your units right before they die. Stalkers are balanced around the fact that HUMANS have limits to how well they can micro.

I'm also excited to see the future of this bot when they demonstrate a terran AI with near-perfect marine/stim/medivac micro.
Post reply on HN