Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Grandmaster level in StarCraft II using multi-agent reinforcement learning

deepmind.com

Post reply on HN
Print view View original

61–70 of 321 posts

Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning

#61

Post by smolder »

username90 wrote: post #54
smolder wrote: post #40

Earlier quoted context omitted.

New players (like when I first played) are likely to select individual larva before they do tutorials or learn the hotkeys, but you're right that high level players would almost never select one directly. Maybe after a hatchery has died and there are still larva remaining?

No, it doesn't select the larvae by dragging, it just selects them instantly from the other side of the map. I'd guess it either has a hotkey for the hatcheries and press it and the larvae key instantly without it showing in the replay, or it has a cheat ability to instantly select larvae.

Oh, interesting. Thanks for clarifying.

Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning

#62

Post by xorfish »

diggan wrote: post #47
Nimitz14 wrote: post #35

The title seems to contradict the subtitle: > Google AI beats top human players at strategy game StarCraft II vs > DeepMind’s AlphaStar beat all but the very best humans at the fast-paced sci-fi video game.

Yeah, subtitle seems much better. My impression before reading was that it did beat the top players but reading the articles makes it clear it beats everyone BUT the top players... Also, this part seems a bit weird from the article: > The AI wasn’t able to beat the best player in the world, as AIs have in chess and Go, but DeepMind considers its benchmark met, and says it has completed the StarCraft II challenge. So…

The difference between top 200 players and the very best players is quite significant in Starcraft II. Some argue that the difference in skill between the best players and a top 200 player is the same as between a top 200 player and a median player.

Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning

#63

Post by username90 »

_f9cu wrote: post #46

Why they wouldn't solve more impactful problems rather than playing games?

Games are a lot easier to work with than real problems since they are easy to simulate and evaluate. So using games as a stepping stone to learn how to make AI's do complex things seems reasonable to me.

Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning

#64

Post by the_af »

ropman76 wrote: post #27
hoseja wrote: post #15

There has always been the issue of interface when playing videogames AI vs human. Either give the human a brain-computer interface or give the AI a mouse, keyboard, monitor, robot hands and a camera. Anything else seems inherently unfair.

Or even a turn based game, where click speed does not matter...

But reaction time in a real time game is also an interesting problem with AI. If they factor out the merely mechanical (the UI itself), reacting to a situation unfolding in real time where you don't have a lot of time to think is a nice test of AI vs human strategic and tactical thinking.

Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning

#65

Post by swarnie_ »

ropman76 wrote: post #27
hoseja wrote: post #15

There has always been the issue of interface when playing videogames AI vs human. Either give the human a brain-computer interface or give the AI a mouse, keyboard, monitor, robot hands and a camera. Anything else seems inherently unfair.

Or even a turn based game, where click speed does not matter...

My understanding is they've capped the AMP/EPM against a reasonably old EU/NA player.

Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning

#66

Post by gwd »

floitsch wrote: post #16
nightcracker wrote: post #5

> After 50 games, however, DeepMind hit a snag. Some players had noticed that three user accounts on the Battle.net gaming platform had played the exact same number of StarCraft II games over a similar time frame — the three accounts that AlphaStar was secretly using. When watching replays of these matches, players noticed that the account owner was performing actions that would be extremely difficult, if not impossi…

These extremely difficult/impossible things didn't really give an advantage. For example, AlphaStar would sometimes click on an object at the border of the screen. For humans that would be almost impossible, because the screen would scroll when the mouse approaches the border. Similarly, AlphaStar would not play with group hotkeys, but use a different technique. However, in none of the analyses, people noticed things…

> These extremely difficult/impossible things didn't really give an advantage.

One of the videos I watched compared APM (Actions Per Minute) with EPM (Effective actions Per Minute). AlphaStar always has them nearly identical, which would be (according to him) basically impossible for humans.

Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning

#67

Post by davinic »

missosoup wrote: post #20
nightcracker wrote: post #5

> After 50 games, however, DeepMind hit a snag. Some players had noticed that three user accounts on the Battle.net gaming platform had played the exact same number of StarCraft II games over a similar time frame — the three accounts that AlphaStar was secretly using. When watching replays of these matches, players noticed that the account owner was performing actions that would be extremely difficult, if not impossi…

I'm not sure this is unfairness. IIRC they put in a fair bit of effort to put it on a level playing field with humans by limiting APM and not allowing it to observe multiple areas simultaneously by spam moving the camera. It might have some minor unfair advantage in terms of being able to click with pixel perfect accuracy, but they're marginal and from watching this project evolve, it's pretty clear that the strategi…

They may be marginal but at this level of competition the margins are where the differentiation lies.

Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning

#69

Post by jplayer01 »

king-rat wrote: post #18

Not being robust to strategies it hasn't seen before is a serious shortcoming in a real time strategy game. That also indicates an interesting flaw in how this model is trained - in the millions of games it plays against itself, how do you ensure that it tries every viable (and some inviable) strategies? Sure, it couldn't best Serral but I wonder how it would fare against Has, a player known for some pretty off the w…

> Not being robust to strategies it hasn't seen before is a serious shortcoming in a real time strategy game.

I'm not sure if you've actually played or followed competitive SC2. This is absolutely normal. Players will pull something completely unexpected out of a hat and win. The losing player will learn from it in future games. That's just how it goes. Unexpected strategies are really hard to counter when you've never seen them before, and they're often employed to directly counter what you're doing right then and there. So you've been countered and dealt a devastating blow, which means figuring out how to come back from that can be hard to impossible. It's a thoroughly human failing in every way. I'd be more concerned if the AI wasn't able to learn to counter it in future matches.

Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning

#70

Post by baddox »

interblag wrote: post #59

This is a really interesting one to digest. As with previous announcements about AlphaStar, much of the feedback (here and elsewhere) is about the fundamental challenge of assessing human vs. machine in an RTS. These points are very valid - stepping back however, this still feels like a pretty incredible accomplishment. I'm a gold league SC2 player, so maybe in the 30th-50th percentile. Three years ago, when DeepMind…

> The speed at which AlphaStar overtook previous AIs seems to me to be nearly unprecedented in AI research.

Is it not simply the case that, before AlphaStar, very little money and effort was being put into developing AIs for Starcraft 2?

Post reply on HN