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

91–100 of 459 posts

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

#91

Post by kolinko »

andreyk wrote: post #74
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…

Also worth noting that it starts by imitation learning from pros. I'd be curious to see if the macro can be learned without imitation; a much harder challenge. Also, playing with full visibility as was mostly the case in the demonstration is quite lame...

It wasn't a full visibility - Alpha had a fog of war. It just saw the whole map at the same time.

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

#92

Post by ionforce »

ForrestN wrote: post #73

Can anyone who has a full context compare this to OpenAI's work on Dota 2? Which is more impressive, both in how far along it is and the relative game difficulty?

This feels more impressive since in SC2 you can pilot many units while in Dota you only (generally) have one. And Deepmind is playing (albeit a slightly older) stock StarCraft II while OpenAI had to play using a very weird ruleset (invulnerable carriers).

Milestones that we have yet to see with Deepmind

- generalize on maps - generalize on races - zero-style training

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

#93

Post by celeritascelery »

andreyk wrote: post #74
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…

Also worth noting that it starts by imitation learning from pros. I'd be curious to see if the macro can be learned without imitation; a much harder challenge. Also, playing with full visibility as was mostly the case in the demonstration is quite lame...

Also I wonder how it handles invisible units. Because as a human player you can see the shimmer if you look close. Can it see that or are they just totally invivisble to it?

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

#94

Post by simmanian »

gamegoblin wrote: post #67
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.

> artificially limit action precision with some sort of virtual mouse that reduced accuracy as APM increased

I like the idea of having action noise that's linearly related to APM

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

#95

Post by b_tterc_p »

ForrestN wrote: post #73

Can anyone who has a full context compare this to OpenAI's work on Dota 2? Which is more impressive, both in how far along it is and the relative game difficulty?

They’re probably comparable and at similar levels of success. Talking about which game offers more entropy isn’t a good metric yet because neither AI seems to be trying to utilize the depth available to them.

E.g. the Dota game had 5 AI working as a team. That feels like it should demonstrate additional competence, but it’s not really clear that they worked as a team.

The Dota game allowed greater variation in starting conditions, but it’s not apparent that the Ai adapts it’s strategy to this well (e.g. hero choice).

Both of them are capable of creating a basic strat and excelling at micro. Neither appears to have great depth of strategy.

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

#96

Post by hughzhang »

andreyk wrote: post #74
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…

Also worth noting that it starts by imitation learning from pros. I'd be curious to see if the macro can be learned without imitation; a much harder challenge. Also, playing with full visibility as was mostly the case in the demonstration is quite lame...

I'll bet you that AlphaStarZero comes out in a year and just learns from scratch.

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

#97

Post by CydeWeys »

hughzhang wrote: post #66
tanilama wrote: post #40

Earlier quoted context omitted.

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.

You play the game as it's written. Come back with another version of StarCraft that isn't so micro-intensive and we can see how the AI does on that.

Chess and Go don't have any form of micro and AIs are nevertheless dominant there.

I'd say, give AI development another year and I wouldn't expect there to be any kind of game, in any genre, that humans can beat AIs at. Whether it's Chess, Go, other classical board games, Civilization, MOBAs, RTSes, FPSs, etc.

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

#98

Post by hughzhang »

Thaxll wrote: post #59
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…

This is exactly what I think, I'd like to see how Alphastar react to "cannon rush" or other weird bo where you need to be "smart" to counter it and just not be based on insane / none human micro.

AlphaStar makes up for its slightly subpar macro with REALLY good at micro. Thus, more micro heavy counters like cheeses are unlikely to beat it.

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

#99

Post by WJW »

kzrdude wrote: post #80
gamegoblin wrote: post #70

Earlier quoted context omitted.

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

Perfect micro bots don't excite me much, because they've existed all along, and it's not an AI task.

There was a "perfect zergling micro vs siege tanks" bot some time ago that would micro lings away from the one that was being fired at by the tanks, thereby negating all the splash damage. The effect was insanely powerful.

But as you say, showing that a bot can have perfect micro is not very interesting. Of course a computer can have better control of well defined tasks like moving a unit away just before it dies, especially doing so for many different units concurrently. What is interesting is the wider strategy and how the computer deals with imperfect information.

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

#100

Post by tialaramex »

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…

So, your link is about Cepheus. It's important to understand that Cepheus isn't AI, it's an (asymptotically close to) optimal strategy for Limit Heads Up ("Limit" means you don't need to choose bet sizes, they are fixed, which makes the problem much simpler), and since poker is a game of probabilities the strategy is probabilistic too.

ie this is like when somebody explains Tic-Tac-Toe, there isn't anything interesting going on inside the machine, the insight was purely mathematical, that there are one or more optimal ways to play this game, and this is one of them.

You can literally look at the strategy right now, you can do it while playing against a program that plays by this strategy. But you won't beat it by doing that, that's the point of this optimal strategy, the best you can do is play this or some other equivalent optimal strategy back, in a home game you'll just pass chips back and forth forever.

In contrast Poker AI is a thing, and at _No Limit_ Heads Up the AI state of the art is clearly better than human, named Libratus - it is nothing like Cepheus, there is no fixed strategy.

For "Full Ring", the game of Poker as you've probably seen it played, which has more than half a dozen independent players, AI would be very challenging, not least because if humans realise they're at a disadvantage it would be essentially impossible to prevent them from colluding with other humans to get an advantage, even to some extent unconsciously.

Post reply on HN