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

151–160 of 321 posts

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

#151

Post by UserIsUnused »

Shaanie wrote: post #103
Symmetry wrote: post #73

Earlier quoted context omitted.

You'd be able to save the time it takes a nerve impulse from head to hand that way. It's not much but apparently it can be significant enough that in some DotA games shorter players are disproportionately successful in the roles requiring the fastest reflexes.

Is that supposed to be a joke? DotA doesn't rely on reflexes nearly enough for that to matter.

Data doesn't lie.

When so many player play a game, even an almost irrelevant advantage can tip the scale.

Or maybe it's a sociological factor, not a phisics ones.

But the data doesn't lie.

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

#152

Post by nullbyte »

Mikeb85 wrote: post #91

As impressive as this is, APM matters a lot in an RTS such as Starcraft and computers have a massive advantage here. I'd like to see them tackle an RTS like Civ where APM doesn't matter whatsoever, only decision making.

Interestingly, AlphaStar has very low APM compared to human players. This is because humans do a lot of insignificant actions when button mashing, whereas AlphaStar is extremely precise with its moves.

That's why when you compare APM graphs between Alpha and a human player, the human almost always ranks higher in actions-per-minute.

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

#154

Post by pps »

300bps wrote: post #136
minblaster wrote: post #81

Earlier quoted context omitted.

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…

264 is not that high. People (if Serral is not a cyborg) can achieve even 1000 APM; and ~300 EPM average for a game.

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

#155

Post by dave_b »

gwd wrote: post #66
floitsch wrote: post #16

Earlier quoted context omitted.

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.

Right, one example I remember from watching the games back in January was stalker micro. The high EPM of the AI allowed it to micro them picture perfectly and blink every single one away right before it died. In doing so it won a battle against impossible odds, and the announcers even commented on how it was way beyond the capabilities of the best players.

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

#156

Post by nemonemo »

diminoten wrote: post #135
dang wrote: post #126

Earlier quoted context omitted.

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...

For those who wonder, the Nature article is here: https://www.nature.com/articles/d41586-019-03298-6

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

#157

Post by papreclip »

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…

IMO it's a testament to how games like SC are collectively and thoroughly "solved" by the community, and how the games aren't that complex after all. I never followed SC or SC2, but my observation of the pro scene and competitive ladder for Warcraft 3 was that cookie cutter strats dominated. Pro players were typically those who executed best, not those who innovated best.

Personally I felt disappointed by the fact that real-time strategy played a pretty minor role in RTS games. If you left the well-beaten path of cookie cutting and tried something new you invariably gave up a pretty obvious advantage to do so.

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

#158

Post by rantwasp »

tomcooks wrote: post #108
rantwasp wrote: post #44

Earlier quoted context omitted.

yes. and the soldiers need to do exactly what you tell them. good luck

this problem would happen also with a human generated strategy so i don't really understand what your point is. food luck

overall you tell them what they should do but you cannot control the micro.

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

#159

Post by jrx »

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…

> This is like if the world's best chess AI had gone from losing high school tournaments to being competitive with Kasparov in less than 3 years.

I don't think it's like that at all. On the high level, there is no "chess AI", "go AI", "image classification AI" and "dexterous manipulation AI". These are all sides of the same coin, that gets significantly better every year. Adding support for the new game or new "environment" to existing deep learning based backbone still requires a bit of engineering work and a few creative tricks to unlock the best possible performance, but the underlying fundamentals are already there and are getting better and better understood.

There is a reason why the progress in AI is so hard to measure. Anytime a next task is solved, there is a crowd saying it's not a "real AI" and that scientists are solving "toy problems". Both statements are totally true. But the underlying substance is that each of these toy problems is of increasing complexity and brings us closer and closer to solving the "real problems", which are mostly so undeniably complex that we couldn't attack them upfront. Still, the speed of progress in the field of AI research is staggering and it's hard to keep up with it even for professional researchers who spend all their waking hours working on these things.

6 years ago we were able to solve some Atari games from pixels. Today, that feels like a trivial exercise compared to modern techniques. With billions of dollars of investment pouring in and steady supply of fresh talent, it is very hard to predict what the pace of research will be in the coming years. It is entirely possible we'll encounter a wall we won't be able to overcome for a very long time. It is also possible that we won't, and in that case we're in for a very interesting next few decades.

Post reply on HN