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

131–140 of 459 posts

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

#131

Post by ionforce »

dfan wrote: post #36
kingbirdy wrote: post #24

Very exciting results. However, I'm a bit confused by this graph [0], could anyone explain how I'm supposed to interpret it? 0: https://deepmind.com/blog/alphastar-mastering-real-time-stra...

I was confused too; it has a weird format that I think hurts comprehension rather than aids it by making you think you're not looking straight at the data. Ignore the fact that the "Training Days" axis is drawn diagonally. The system is creating about 40 agents per day; by the end of day 14 it's made 610 or so. The graph shows, for any given time of training (vertical axis, going down), what is the distribution of tr…

I think it's to help illustrate the time dimension as going forward rather than something that goes up and down. And also to not measure the hills against some global X-axis. It is confusing.

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

#132

Post by CydeWeys »

gambler wrote: post #128
CydeWeys wrote: post #90

Earlier quoted context omitted.

For now. Give them another month. This is like AlphaGo vs Fan Hui all over again -- people knocked that accomplishment at the time because he was just a master, not one of the top players in the world. Well, not much longer, AlphaGo beat Lee Sedol, the best player in the world. The ceiling here is going to be incredibly high, much higher than the level of play that people are capable of, even when restricted to a sin…

It's not the accomplishment that people knock. It's the spin, the inaccurate article titles and the hype.

It doesn't seem like hype to me -- it seems like a genuine, significant accomplishment. Sure, they might not be able to beat the best pro players consistently right now, but I suspect that is right around the corner. Would you rather they stay completely mum until they've reached that goal too? And why? I'd rather know now, and then be able to follow along as it gets better and beats higher and higher-ranked players.

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

#133

Post by loser777 »

hughzhang wrote: post #96
andreyk wrote: post #74

Earlier quoted context omitted.

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.

I'll take you up on that bet; they started with a version that tried to learn from scratch they seemed to have scrapped that approach.

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

#134

Post by olliej »

methodover wrote: post #121
olliej wrote: post #78

Earlier quoted context omitted.

it seems like in some cases at least it didn't have to move the camera (it had direct interfaces) which for some of the stalker micro battles (especially in game 3 or 4?) the battles were larger than the screen space -- it would not have been possible to micro that well if your control interface limited what you can control or where you can place them.

This is a great point, and something that seems a bit lost in the discussion: In StarCraft 2, the game IS the interface. That is to say, the developers have constructed the game in such a way as to be difficult to control; and human mastery of the interface is a large percentage of the game. Strategy in the game is important, of course -- but this is not chess, where human beings are not limited by the interface of t…

That would actually be an interesting thing for someone from blizzard to do, get two similarly skilled high level players, and compare the win/loss rate by doing two 7 games matches with each player having a match with a 10% increased view size, and see what the impact is.

Essentially try to quantify the advantage of increased view area.

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

#135

Post by disconcision »

justfor1comment wrote: post #48
cellis wrote: post #9

I would really like to see this for Age of Empires II. I think AOE has far more races and is a far more complex game ( although I'm biased because I haven't played SC2 as much as AOEII ).

I have played both games and a fan of both. Starcraft is definitely more complex than AoE for AI development and that's why the researchers must have chosen it. The complexity of AI depends on how many potential decisions you can make at any point of time. Here are a few reasons why: 1) Starcraft races have completely different build trees and different advantages. This has a large cascading effect of early decisions…

what do you mean exactly by "The Starcraft map terrain is hierarchical"? do you mean there are more choke points?

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

#136

Post by celeritascelery »

shawnz wrote: post #120
celeritascelery wrote: post #112

Earlier quoted context omitted.

You can eliminate that advantage by letting the AI only see the unit information for things on screen, like they did in the last game.

No, that doesn't eliminate the advantage -- that's what I'm trying to say. Even if you make the AI move the screen around manually and only let it enumerate units that are on-screen, that's still going to take roughly as long as just enumerating through all the units on the map in one go. It's just a matter of executing "foreach all_units" versus "foreach screens { foreach units_on_screen }". In either case a compute…

I get what your saying. But screen movement is rate limited (meaning you can't loop through all possible screen positions in 1ms) so you have to actively choose where you want to focus, just like a human player. Think of it more like calls to a web server then "foreach screens".

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

#137

Post by sl1ck731 »

pmontra wrote: post #129
gamegoblin wrote: post #67

Earlier quoted context omitted.

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.

I understand the spirit of the proposal but that would be like limiting a computer to add at most two numbers per second. It's OK if we want an interesting contest against humans but it wouldn't be a fair estimate of a computer math capability. It's also not the point of using computers to do math instead of a room full of accountants. I'm OK with the AI going as fast as it can and play superhuman strategies because…

The purpose of limiting speed isn't to make an interesting contest, it is to accurately compare the "math" instead of the speed the math is done at.

It isn't surprising that its fast, the surprising part is that it can make human-like decisions. The only way to compare whether its thinking is human-like is to restrain it from "brute forcing" the contest through speed.

The model has likely learned that the faster it does things the better the outcome. What it needs to be measured on is strategy.

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

#138

Post by thomasahle »

pmontra wrote: post #129
gamegoblin wrote: post #67

Earlier quoted context omitted.

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.

I understand the spirit of the proposal but that would be like limiting a computer to add at most two numbers per second. It's OK if we want an interesting contest against humans but it wouldn't be a fair estimate of a computer math capability. It's also not the point of using computers to do math instead of a room full of accountants. I'm OK with the AI going as fast as it can and play superhuman strategies because…

You are right, but the point here is to force it to win by pure decision making. Having an AI play a game was always about challenging ourselves to improve our understanding of intelligence. Limiting APM is just another way to force us to come up with new ideas.

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

#139

Post by olliej »

ionforce wrote: post #130
olliej wrote: post #71

The gameplay was really interesting - i wonder if we'll start seeing the over-saturation of the main prior to first expand in pro games?

There are three things this seems to do. And what's changed is the perceived value of these. 1) Increased mining rate. Although there's a prescribed "maximum", as I understand it adding more workers, up to some limit, does yield more minerals beyond the prescribed. 2) Buffer against harassment. If you are over-saturated and lose two probes, you rate of income isn't affected. 3) Bootstrapping an expansion. All of the…

Right, I get that it AlphaStar has decided this is sensible, I just wonder if we'll start seeing pros adopt something similar?

I'm also more generally curious as to what the cutoff point at which adding an additional probe ceases having any value.

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

#140

Post by shawnz »

celeritascelery wrote: post #136
shawnz wrote: post #120

Earlier quoted context omitted.

No, that doesn't eliminate the advantage -- that's what I'm trying to say. Even if you make the AI move the screen around manually and only let it enumerate units that are on-screen, that's still going to take roughly as long as just enumerating through all the units on the map in one go. It's just a matter of executing "foreach all_units" versus "foreach screens { foreach units_on_screen }". In either case a compute…

I get what your saying. But screen movement is rate limited (meaning you can't loop through all possible screen positions in 1ms) so you have to actively choose where you want to focus, just like a human player. Think of it more like calls to a web server then "foreach screens".

Can't you click on the minimap to move the camera instantly anywhere on the map?

EDIT: I guess you would still have to wait for the next frame to get rendered, which could add up. True, that does change things a bit, but of course a computer could still do that way faster than a human.

Post reply on HN