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

131–140 of 321 posts

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

#131

Post by UnFleshedOne »

Enginerrrd wrote: post #95
kingkawn wrote: post #89

Earlier quoted context omitted.

Yes, the point of the entire project was for the system to see if it can win. If we have reached the point where to even risk a loss requires implementing artificial restraints on the AI...well...

They aren't really artificial restraints though, more like artificial advantages without them. The interface delay challenges are pretty relevant to making things fair in almost ANY competition. The physical part of the interface is an essential part of the game here. You aren't really testing the thing you really want to test otherwise. You could probably play tennis pretty well against Nadal if you made him wear go…

I wonder if implementing tactical pause would eliminate interface advantages. Players can pause game, scroll around map and give orders to units before unpausing and watching them execute.

It will be a different game, but you can see how AI does against humans tactically and strategically.

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

#132

Post by Mirioron »

baddox wrote: post #70
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?

What makes this amazing isn't specific to StarCraft 2. AI in strategy games has been really lackluster. I can't think of a single example of a strategy game where an AI was competitive against experienced players due to strategy and tactics, rather than inhuman speed, accuracy or cheating. So it's not just about AI in StarCraft 2, but rather AI in essentially any (strategy) game. Now we have an example of an AI that can compete with real players.

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

#133

Post by jcampbell1 »

jamra wrote: post #71
username90 wrote: post #31

Earlier quoted context omitted.

They are testing the AI's ability to do tactics and strategy, not motor and visual tasks. It has built in delay and needs to move around the map to gather information just like a human, so it doesn't have any significant unfair advantages. Edit: Note that the version they sent out to the ladder had significant larger delay, significant lower APM, and didn't get any information not visible on the screen unlike the fir…

However the computer can macro while in a fight which is something people can’t dI. We would miss the fight and lose the game. It’s not just a tactics game. Attention span and where your eyes are matter.

Elite players do this all the time. Serral would use his standard tactic of attacking in two places as the same time, and alpha star couldn’t figure out the best way to deal with it. When alpha star did the same thing to him, he would mitigate the smaller attack and even predict alphastar’s escape route and crush it.

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

#134

Post by readparryrepost »

Love the work done into this, SC2 is such a 'human' game I'm impressed that it can be so successful but I'm wondering whether the model takes the raw graphical information or whether it takes some kind of full map representation. Some kind of machine representation might feel like cheating just a little as it's not quite competing on the same playing field as a human player.

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

#135

Post by diminoten »

dang wrote: post #126
jplayer01 wrote: post #42

Honestly, the article needs to be replaced with https://deepmind.com/blog/article/AlphaStar-Grandmaster-leve... which actually goes into some technical detail. Nature.com's article is purely for laypersons and, imo, not particularly useful for HN's crowd because of how little insight it gives. It also provides the paper and an archive of all of the AI's matches for anybody who wants to take a closer look. These can b…

This comment was originally posted on https://news.ycombinator.com/item?id=21408024 , but we've merged it into the earlier submission, which used the link you mentioned.

The viewers of HN need Nature just as much as anybody, stop deluding yourself into thinking this is some kind of ivory tower...

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

#136

Post by 300bps »

minblaster wrote: post #81
baddox wrote: post #70

Earlier quoted context omitted.

> 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?

Starcraft is an incredibly complex game. 10^26 possible moves at any point (you can click/drag anywhere on the screen, pressing a keyboard button as you do so), imperfect information, real-time constraints, etc.

Starcraft is an incredibly complex game.

Even basic strategies will win if they’re done faster. APM (actions per minute) is a very significant factor into who is winning. Apparently they limited their AI player to 264 APM but that’s still incredibly high and done with machine level consistency. That’s almost 4.5 actions per second!! I know there are human level players at and probably above that level but that really allows for basic strategies to win out.

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

#137

Post by Mirioron »

ionforce wrote: post #117
bsaul wrote: post #58

Has anyone read the actual paper ? This summary really makes it look like "mission accomplished", but this was much much more interesting than that. We saw AI do "obviously stupid things", and we also saw them improve a lot in the middle of the trial, as many youtubers showed. AI was also much more interesting when playing the protoss race, and really felt like it was responding to the opponents actions, and the othe…

> But most surprising is that it didn't make any "breathtaking" moves or actions, as opposed to AlphaGO. I don't play any competitive StarCraft so my view might be moot but I was surprised at the number of siege tanks it uses. It made me wonder if there's some critical advantage to having so many tanks stacked up in a line so that the splash is spread out. Also I find it weird that it did not build any marauders at a…

>Also I find it weird that it did not build any marauders at all, in any of the games I've seen.

This is off-topic, but I was thinking about this the other day - couldn't AI be used to balance a competitive game in this sense? Imagine that the AI becomes so good that human players very rarely win against the AI in a best of 7 series. Then we find out that AI doesn't ever build a specific unit. That would be a pretty strong indicator that said unit isn't good enough compared to the rest.

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

#138

Post by TremendousJudge »

dannypgh wrote: post #122
TremendousJudge wrote: post #113

Earlier quoted context omitted.

>Machines on the other side, can be scaled arbitrarily. Once you've built a small crane, you can build even increasing ones, it's just a function of money and interest. It doesn't matter how much money or interest we have, but right now it isn't technically feasible to build a 36000 km tall crane (also known as a space elevator). Humanity simply couldn't get it done even if we poured all our current resources into th…

> Following the analogy, a general purpose AI simply isn't a bigger Deep Blue or AlphaGo; it's probably something different that requires knowledge that we currently don't have. I agree with this, but it isn't clear to me that a general AI will have a significantly different impact on society than a world where task-specific well performing AIs are easy for anyone to develop. Sure, a general AI has a set of propertie…

You're right. Of course, we're not yet in a world where _task-specific well performing AIs are easy for anyone to develop_, but we're getting there and looks feasible. A 500 meter crane.

However, I disagree that the impact is the same. I think that the difference between a lot of specific jobs being automated and the world being run by a MULTIVAC world optimizer is pretty big.

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

#139

Post by UnFleshedOne »

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…

I suspect if they remove artificial limitations (like APM limit and no screen jumping), it will be unbeatable.

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

#140

Post by jcampbell1 »

I know this is an endless discussion about fairness, but they handicapped it to have the capability in terms of EAPM of the worlds best player at peak. The result is that it could beat all but the top players. While the mechanics of not using hot keys was strange, I never saw it do anything the elite players couldn’t do.

It is worth watching the match between alpha star and Serral who is current best player. Serral beats it like a walk in the park.

https://m.youtube.com/watch?v=_BOp10v8kuM

Post reply on HN