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

DeepMind and Blizzard to release StarCraft II as an AI research environment

deepmind.com

Post reply on HN
Print view View original

191–200 of 344 posts

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#191

Post by cryptrash »

I'm pretty excited about this. I think some kids out there will really enjoy an environment like this to mess with, and maybe learn a thing or two about machine learning along the way.

Starcraft is a really fun game, and I think it's enough to engage kids a little more than something like Minecraft where there's plenty of room for some cool ML hacking, but not enough stimulation from it. Instead of just seeing blocks here or there or whatever, starcraft has hard goals that will force them to use critical thinking skills, their knowledge of the game, their own personal strategic insights, and the ML skills they accrue.

So exciting! Love the feature layer idea also, well done!

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#192

Post by vtange »

burke wrote: post #132
theptip wrote: post #122

This is pretty interesting. DeepMind’s last triumph (beating the best human Go players with AlphaGo) is impressive, but Go is a great fit for neural networks as they stand today; it’s stateless, so you can fully evaluate your position based on the state of the board at a given turn. That’s not a good fit for most real-world problems, where you have to remember something that happened in the past. E.g. the ‘fog of war…

> When Google’s AI can beat a human at StarCraft, it’s time to be very afraid. I don't actually agree with this. Unlike Go, StarCraft is not only a game of strategy; "micro" (micro-managed tactics, basically) also plays a big role. An AI is going to be able to issue a LOT more commands per second than even the most skilled humans, giving them a natural tactical advantage. Strategy is more difficult for an AI, but not…

That reminds me of a video demonstrating two "hardest" setting AI's against each other in Age of Empires II. https://www.youtube.com/watch?v=DqiOQ1dAhL4

One AI won simply because it abused the fact it could spam monks and use the monks in a manner no human could ever achieve

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#193

Post by dwaltrip »

mmanfrin wrote: post #184
theptip wrote: post #122

This is pretty interesting. DeepMind’s last triumph (beating the best human Go players with AlphaGo) is impressive, but Go is a great fit for neural networks as they stand today; it’s stateless, so you can fully evaluate your position based on the state of the board at a given turn. That’s not a good fit for most real-world problems, where you have to remember something that happened in the past. E.g. the ‘fog of war…

Really rudimentary AIs are already significantly beyond the skill of humans (in terms of micro, at least). https://www.youtube.com/watch?v=IKVFZ28ybQs

They are quite terrible at all of the other aspects: macro, broad strategy, tempo & timing, planning tactical surprises, etc.

This results in a very low overall competency, when it comes to winning games against highly skilled opponents.

It will be a challenge for researchers to improve performance in these areas. The problem space is very complex -- it makes solving Go look like a cake walk in comparison.

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#194

Post by ygra »

mmanfrin wrote: post #184
theptip wrote: post #122

This is pretty interesting. DeepMind’s last triumph (beating the best human Go players with AlphaGo) is impressive, but Go is a great fit for neural networks as they stand today; it’s stateless, so you can fully evaluate your position based on the state of the board at a given turn. That’s not a good fit for most real-world problems, where you have to remember something that happened in the past. E.g. the ‘fog of war…

Really rudimentary AIs are already significantly beyond the skill of humans (in terms of micro, at least). https://www.youtube.com/watch?v=IKVFZ28ybQs

As you note, that's only micro, and it's the easy part since you can do most of that with rather simple rules and just high apm (which is where the benefit compared to human players comes from). The interesting part for AI is how to get there, the longer-term planning, recognizing the enemy's strategy based on what it observes, reacting appropriately, etc. So far those are the things AIs have trouble with.

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#195

Post by somerandomness »

arcticfox wrote: post #134
burke wrote: post #132

Earlier quoted context omitted.

> When Google’s AI can beat a human at StarCraft, it’s time to be very afraid. I don't actually agree with this. Unlike Go, StarCraft is not only a game of strategy; "micro" (micro-managed tactics, basically) also plays a big role. An AI is going to be able to issue a LOT more commands per second than even the most skilled humans, giving them a natural tactical advantage. Strategy is more difficult for an AI, but not…

I agree. I think you'd have to limit that machine's APM to somewhere around the human limit, and make it choose which actions it wants to spend its time on. Otherwise the AI is eventually just going to absolutely destroy humans with micro, which is not remotely interesting. We've known transistors were faster than fingers for ages.

'Computers are capable of extremely fast control, but that doesn’t necessarily demonstrate intelligence, so agents must interact with the game within limits of human dexterity in terms of “Actions Per Minute”.'

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#196

Post by plg »

I understand the challenge, and the importance of the proof-of-principle. But again? Having done Atari games, then Go, at what point exactly does google deepmind start attacking some real world problems of consequence?

Or maybe the answer is never, other companies are supposed to do the hard work? We only play games?

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#197

Post by ygra »

headcanon wrote: post #123
cosarara97 wrote: post #111

Earlier quoted context omitted.

What about APM? Doesn't the speed at which the AI can input commands give it a big advantage?

Definitely, but my guess is that Starcraft AI's are really good at Macro play (building the right units and tech trees), but at the upper levels of SC players win or lose in Micro play (specific positioning of units), which is much harder for an AI to accomplish well, since there are a lot of little tricks. Basically, Macro can be programmed easily, but Micro requires the player to respond creatively. http://wiki.tea…

It's actually the other way around, I'd say. Individual unit control follows very naturally when you have unlimited APM. And most of the time you can define simple and good criteria on how to position the units (e.g. concave, or exactly the right distance apart to avoid splash damage, or one unit a tiny bit more towards the enemy to be the first one targeted by incoming fire, ...). Build orders can be programmed, yes, but transitioning between strategies properly based on observations and guessing or judging the enemy's strategy is quite hard.

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#198

Post by theptip »

burke wrote: post #132
theptip wrote: post #122

This is pretty interesting. DeepMind’s last triumph (beating the best human Go players with AlphaGo) is impressive, but Go is a great fit for neural networks as they stand today; it’s stateless, so you can fully evaluate your position based on the state of the board at a given turn. That’s not a good fit for most real-world problems, where you have to remember something that happened in the past. E.g. the ‘fog of war…

> When Google’s AI can beat a human at StarCraft, it’s time to be very afraid. I don't actually agree with this. Unlike Go, StarCraft is not only a game of strategy; "micro" (micro-managed tactics, basically) also plays a big role. An AI is going to be able to issue a LOT more commands per second than even the most skilled humans, giving them a natural tactical advantage. Strategy is more difficult for an AI, but not…

Agreed that micro is a big advantage that AIs have held in previous AI vs. Human StarCraft contests, but the OP stated that the SC2 research environment will limit the AI to (elite) human APM levels, so that edge will be somewhat blunted. It's probably fair to question whether all actions are counted equally; I could believe that an AI could allocate their action budget more widely than a human can, even while hitting the same total APM.

More importantly, in my opinion, I'm not aware of any other AIs that have been competitive at the StarCraft problem using a Neural-Net-based implementation; from talking to PhDs in the field (but not from direct technical experience, so take this with a pinch of salt), my impression is that state-of-the-art RNNs just don't have the ability to encode the history of the game-world in a way that would enable them to be competitive. So it will require significant advances to the theoretical models to be able to compete using the sort of implementation that DeepMind will build.

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#199

Post by theptip »

trjordan wrote: post #154
lordnacho wrote: post #139

Earlier quoted context omitted.

> Otherwise the AI is eventually just going to absolutely destroy humans with micro, which is not remotely interesting. If you could issue as many orders as you wanted, what would the optimal strategy be?

A big part of Starcraft is that certain units counter other units. Tanks counter zerglings, because they do splash damage to a bunch of them at once. Here's what you can do with infinite APM: https://www.youtube.com/watch?v=IKVFZ28ybQs It's just broken. It's not even the same game.

I enjoyed this, thanks for sharing. Pretty cool.

Re: DeepMind and Blizzard to release StarCraft II as an AI research environment

#200

Post by theptip »

qznc wrote: post #187
empath75 wrote: post #182

Earlier quoted context omitted.

Even if you don't imagine robots becoming self aware and deciding to kill humans on their own, you can imagine a fleet of drones and self-driving tanks controlled by a deep learning network. They don't need to understand what they're doing to make effective tactical decisions. If the US doesn't do this, someone else probably will. We're going to see an AI-based blitzkrieg attack in our lifetimes. Once you can launch…

We have not seen the bomb-carrying drones yet. That is entirely possible right now, but IS has not used that so far.

Actually, this has happened already: https://www.washingtonpost.com/news/checkpoint/wp/2016/10/11...
Post reply on HN