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

351–360 of 459 posts

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

#351

Post by fandango »

rkagerer wrote: post #326
rcheu wrote: post #46

This is really impressive, I didn't expect starcraft to be played this well by a machine learning based AI. I'm excited to read the paper when it comes out! That said, I'm not sure I agree that it was winning mainly due to better decision making. For context, I've been ranked in the top 0.1% of players and beaten pros in Starcraft 2, and also work as a machine learning engineer. The stalker micro in particular looked…

Yeah that stalker micro really showcases a particular advantage leveraged by the AI. I'd love to watch the results of constraining the AI so instead of seeing the whole map at once it has to pan around the same way a human would to get updated information on each battle. Counting those "info-gathering" window pans against the actions tally might yield slightly fairer APM metrics. (EDIT: Turns out they built a new age…

I agree. Most RTS games feel constrained because of the limited viewport. Supreme Commander has a nice feature where you can zoom all the way out at any time.

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

#353

Post by a_imho »

RockofStrength wrote: post #211

If they don't cap the apm at 300 or so, this means nothing. I am not impressed with super speed, only decision making matters. Deepmind, you can do better.

AlphaZero was set up against Stockfish similarly on unequal footing.

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

#354

Post by jabl »

anabis wrote: post #308
alasdair_ wrote: post #232

What are the games that, so far, still look like they will be too difficult for ML to play them at the highest level? I know Go was held to be this kind of game for a long time and is now close to being dominated by AI. Magic: the gathering perhaps?

non zero-sum games seems like a logical next step.

Any (reasonably) popular games that are non zero sum?

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

#355

Post by nurettin »

confiscate wrote: post #275
gowld wrote: post #252

Earlier quoted context omitted.

What happens if a human tries to use the API with a custom UI of the human's own choosing? Such a UI might not exist yet, but are there ideas for more efficient UIs that could be built?

Yes I am curious of this too. What happens if the human has a giant TV screen that can see the whole map at once Or, what if we slow down the game, so that the human can actually pause the game each second and consider what to do next. That's basically what the computer is allowed to do

Giant tv:

Macro-wise, it would be like an unwieldly minimap which already exists so people can get a sense of where the enemy is moving. With a giant screen, information is not focused on a small area, so you are limited to your FOV. Minimap which shows unit strength in terms of armor hp or shields as well as placement would be ideal information.

Micro-wise, it would be like sitting in front of a giant text display looking at a whole book. You still have to focus on a small section to read it.

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

#356

Post by yvdriess »

fandango wrote: post #351
rkagerer wrote: post #326

Earlier quoted context omitted.

Yeah that stalker micro really showcases a particular advantage leveraged by the AI. I'd love to watch the results of constraining the AI so instead of seeing the whole map at once it has to pan around the same way a human would to get updated information on each battle. Counting those "info-gathering" window pans against the actions tally might yield slightly fairer APM metrics. (EDIT: Turns out they built a new age…

I agree. Most RTS games feel constrained because of the limited viewport. Supreme Commander has a nice feature where you can zoom all the way out at any time.

And a very important part to SupCom's zoom feature is that at a certain zoom level it switches to a rich visual overlay of unit icons and pending/queued orders.

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

#357

Post by EGreg »

I wonder how far AI can progress. Can for example five robots, built to have insane reaction times and agility, outperform and safely subdue an entire army of 1 million humans equipped with the latest melee weapons?

Or how about a tiny flying robot with millisecond reaction times in a room with a crowd of people trying to catch it, being able to eg buzz and tag everyone without being so much as touched?

How about one robot which builds replicas or otherwise organizes some massive “real time strategy growth” across a city, versus the entire city and its police and army being called in? With the robot swarms coordinating distributed superhuman strategies and timing? I feel that, whatever we are discovering now, aliens who make it to Earth will have had hundreds of years advantage on that. It seems Monte Carlo Tree Search is the best we’ve got against the aliens, for now.

Think Ender’s game but for real. It will require something like that.

Anyone also remember the narration in Edge of Tomorrow? There the aliens had the additional advantage of resetting the clock to the beginning thus nullifying any win, but really with trillions of games being played by a league against itself, that rare “restart” seems quaint versus what we have here.

Or over eons perhaps long term strategy with mining asteroids with Von Neumann probes competing.

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

#358

Post by tjoff »

gpm wrote: post #218
tjoff wrote: post #103

Earlier quoted context omitted.

Isn't the point of a cannon rush to build the first cannons where they can't be seen?

Surprisingly not. The trick is usually to build pylons (or other cannons) such that they protect the cannons from being attacked by probes. Building them out of sight is usually too slow as a rush. Still, he didn't do that either.

In the beginning of SCII I only saw people trying to hide it. But I guess the strategy evolved, interesting.

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

#359

Post by TulliusCicero »

celeritascelery wrote: post #88
Jyaif wrote: post #83

Earlier quoted context omitted.

The AI lost because it completely messed up the response to the immortal drop, nothing to do with micro.

Mana got himself in the same situation where he was surrounded by stalkers on multiple sides, but this time the micro wasn’t so crazy that he couldn’t manage it, and he was able to take on one group at a time. The immortal drop, while unanswered, was not really that effectual.

The immortal drop let him keep AlphaStar occupied while he built up a critical mass of immortals (it becomes harder and harder to effectively micro stalkers against immortals as numbers go up, probably even for an AI), then let him put AlphaStar in an awkward position when it was camping near where the warp prism was hiding.

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

#360

Post by TulliusCicero »

nopinsight wrote: post #313
rcheu wrote: post #46

This is really impressive, I didn't expect starcraft to be played this well by a machine learning based AI. I'm excited to read the paper when it comes out! That said, I'm not sure I agree that it was winning mainly due to better decision making. For context, I've been ranked in the top 0.1% of players and beaten pros in Starcraft 2, and also work as a machine learning engineer. The stalker micro in particular looked…

One macro technique used by AlphaStar agents that is not used by human pros is building extra workers beyond currently exploitable capacity. This gives them reserves when attacked and some workers killed. They can also ramp up mining at a new base quickly by moving the extra workers there. Apparently the benefits outweigh the costs for these workers for AlphaStar. It will be interesting to see if some pros decide to…

Yeah, it looked like Mana was copying this behavior somewhat in the live game.
Post reply on HN