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

DeepMind and Blizzard Open StarCraft II as an AI Research Environment

deepmind.com

Post reply on HN
Print view View original

221–230 of 283 posts

Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment

#221

Post by 36bydesign »

littlestymaar wrote: post #184
TulliusCicero wrote: post #164

Earlier quoted context omitted.

As someone who probably has played at a higher level than you I disagree. Yes, it's true that mechanics are a large determinant in who wins between people. But pro humans are not easily thrown off by odd or novel strategies or tactics. They can react to things that introduce small wrenches into their build order without serious issues. Players can even adapt to things they've never seen before. The issue with Starcra…

> But pro humans are not easily thrown off by odd or novel strategies or tactics. In tournament, with all the inducted stress they definitely do : see Lilbow vs Life in blizzcon 2015, or the whole run of Symbol in Iron Squid one. For BW, see Flash vs Stork in whatever MSL or OSL finals (in 2009 or 2010 I think). > the neural nets will have nothing to account for, say, a mid-game cannon rush, or whatever. The AI just…

He said pros are “not easily” thrown off by novel strategies, not that they are “never” thrown off by such, so your examples are the exceptions that prove the rule.

FWIW I think you also drastically underestimate how many things the AI has to take into account. It isn’t just how many 2-2 zerglings you need to destroy a cannon, it’s making educated guesses of what you’re opponent is doing while you’re attacking the cannons, or how the terrain affects how you can attack, or what units the opponent may have be in the fog of war ready to ambush. Represting all these factors, let alone calculating them, is no trivial task.

Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment

#222

Post by 36bydesign »

gambler wrote: post #188
qub1t wrote: post #179

Earlier quoted context omitted.

I used to be pretty active on iccup, and I was a masters-level sc2 player for a while during the beta and when it was first released. So I'm definitely familiar with starcraft and what it takes to become a good player. I think you're misunderstanding a big part of what is "easy" and "difficult" for humans vs ai. Yes, go is absolutely a more challenging games for humans than starcraft (I also play go, although not ver…

>The big advancement in alphago is that by using deep learning it is able to evaluate different board-states without doing any search, using a neural net. It still uses a Monte-Carlo Tree Search to get to the level where it can beat human pro players. >Starcraft is real-time, there are tons of different actions you can take, the actions are not independent (pressing attack does something different if you have a unit…

What are their other options besides Starcraft2? This doesn’t seem like a PR stunt (not that the PR isn’t a bonus), but there’s already a history of AI competitions for Brood War, the game is more balanced than arguably any other RTS, and even though it is “primitive” as a strategy game in your estimation, AI isn’t ready to tackle a more advanced strategy game.

Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment

#223

Post by aerovistae »

sidusknight wrote: post #212
aerovistae wrote: post #209

Earlier quoted context omitted.

In what universe is taking 10,000 actions per minute an easier problem for a neural net than 100 such actions?

Have you played SC2 before? It's hard to explain if you haven't.

Yes, I have.

Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment

#224

Post by gwern »

gambler wrote: post #188
qub1t wrote: post #179

Earlier quoted context omitted.

I used to be pretty active on iccup, and I was a masters-level sc2 player for a while during the beta and when it was first released. So I'm definitely familiar with starcraft and what it takes to become a good player. I think you're misunderstanding a big part of what is "easy" and "difficult" for humans vs ai. Yes, go is absolutely a more challenging games for humans than starcraft (I also play go, although not ver…

>The big advancement in alphago is that by using deep learning it is able to evaluate different board-states without doing any search, using a neural net. It still uses a Monte-Carlo Tree Search to get to the level where it can beat human pro players. >Starcraft is real-time, there are tons of different actions you can take, the actions are not independent (pressing attack does something different if you have a unit…

> It still uses a Monte-Carlo Tree Search to get to the level where it can beat human pro players.

I'm not sure this was true of the first AlphaGo, probably wasn't true of the Sedol AlphaGo, and definitely isn't true of Master.

Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment

#225

Post by smallnamespace »

gambler wrote: post #194
teraflop wrote: post #131

Earlier quoted context omitted.

Technically you're right, but there's a real qualitative difference. Each "tick" in a game like StarCraft is on the order of tens of milliseconds. When you send out an army to attack your opponent, it's quite possible that the actual confrontation won't happen until 10,000 ticks in the future. Also, the dimensionality of the state space in a "continuous" game is orders of magnitude larger. In a game like chess or Go,…

To the best of my knowledge, the only thing in SC2 that requires pixel-level precision is selecting units. Everything else can just as easily be represented as a fairly coarse grid with no loss of expressiveness. Buildings are explicitly snapped to a grid, and moving your units several pixels to either side simply doesn't matter. So calling SC2 "continuous" in terms of space is misleading. I don't think there is anyt…

Even with the restrictions you put in place, SC2's state space is much larger than any board game.

A typical game might last 15 minutes = 54000 60fps frames and a typical map is larger than 10k x 10k in terms of 'coarse units'.

For any given frame of animation there are at least a million valid actions - if you have 10 units then you can move any subset of those units to any place on your screen.

Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment

#226

Post by knicholes »

littlestymaar wrote: post #184
TulliusCicero wrote: post #164

Earlier quoted context omitted.

As someone who probably has played at a higher level than you I disagree. Yes, it's true that mechanics are a large determinant in who wins between people. But pro humans are not easily thrown off by odd or novel strategies or tactics. They can react to things that introduce small wrenches into their build order without serious issues. Players can even adapt to things they've never seen before. The issue with Starcra…

> But pro humans are not easily thrown off by odd or novel strategies or tactics. In tournament, with all the inducted stress they definitely do : see Lilbow vs Life in blizzcon 2015, or the whole run of Symbol in Iron Squid one. For BW, see Flash vs Stork in whatever MSL or OSL finals (in 2009 or 2010 I think). > the neural nets will have nothing to account for, say, a mid-game cannon rush, or whatever. The AI just…

I'm pretty sure you're aware that Life has been banned from professional SCII for match fixing, but if not, I just want to throw that in there.

Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment

#227

Post by themacguffinman »

jtraffic wrote: post #216
JefeChulo wrote: post #30

"so agents must interact with the game within limits of human dexterity in terms of “Actions Per Minute”." I am really glad they are limiting APM because otherwise things just get stupid.

Philosophically, I wonder if it's better to just acknowledge the differences between AI and humans, and let them play to their strengths. It seems common to think that we need to constrain AI in certain ways to be more like humans, but the constraints are always artificial. APM is one constraint, but what about working memory? What about multithreading? We already allow the AI access to computational resources humans…

I don't think they're constraining APM to make the AI more human-like. It seems more like they're controlling a variable, so that if the AI wins, they know it wasn't just because the AI could out-click a human.

Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment

#228

Post by Shoop »

gwern wrote: post #224
gambler wrote: post #188

Earlier quoted context omitted.

>The big advancement in alphago is that by using deep learning it is able to evaluate different board-states without doing any search, using a neural net. It still uses a Monte-Carlo Tree Search to get to the level where it can beat human pro players. >Starcraft is real-time, there are tons of different actions you can take, the actions are not independent (pressing attack does something different if you have a unit…

> It still uses a Monte-Carlo Tree Search to get to the level where it can beat human pro players. I'm not sure this was true of the first AlphaGo, probably wasn't true of the Sedol AlphaGo, and definitely isn't true of Master.

Do you have an article about this? I never heard that AlphaGo moved away from MCTS.

Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment

#229

Post by jtolmar »

sidusknight wrote: post #211
jtolmar wrote: post #204

Earlier quoted context omitted.

The preferred opening for Protoss in PvZ (on most maps) is the forge fast-expand. If the Zerg player doesn't want to play an economic game in response, they have a variety of all-in strategies available. There is a lengthy article on Team Liquid about how Protoss should respond to these. http://wiki.teamliquid.net/starcraft/Protoss_Counter_to_Zerg... What I'd note here is that: 1. It's a rather long list. 2. Good sco…

Protoss hasn't went FEE PvZ in a long time. It used to be good, though.

Well, egg on my face then. What's the current choice?

Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment

#230

Post by gambler »

smallnamespace wrote: post #225
gambler wrote: post #194

Earlier quoted context omitted.

To the best of my knowledge, the only thing in SC2 that requires pixel-level precision is selecting units. Everything else can just as easily be represented as a fairly coarse grid with no loss of expressiveness. Buildings are explicitly snapped to a grid, and moving your units several pixels to either side simply doesn't matter. So calling SC2 "continuous" in terms of space is misleading. I don't think there is anyt…

Even with the restrictions you put in place, SC2's state space is much larger than any board game. A typical game might last 15 minutes = 54000 60fps frames and a typical map is larger than 10k x 10k in terms of 'coarse units'. For any given frame of animation there are at least a million valid actions - if you have 10 units then you can move any subset of those units to any place on your screen.

>Even with the restrictions you put in place, SC2's state space is much larger than any board game.

That depends entirely on how you represent it. You're forgetting that there are plenty of AIs that actually play the game right now. They just don't use the same kind of "interface".

>For any given frame of animation there are at least a million valid actions

That's Google's marketing cool aid. "Actions" that produce the exact same result cannot be meaningfully counted as separate actions, especially when you're trying to compare them to board game moves.

Post reply on HN