DeepMind and Blizzard to release StarCraft II as an AI research environment • Hacker News Board

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

#161

Post by hooloovoo_zoo » Fri, Nov 04, 2016, 10:03 PM UTC

bradleyjg wrote: post #100

tdaltonc wrote: post #90

I'd love to see a e-sport league where the teams are AI human hybrids (Centaur teams). We know that AI human hybrid teams are great at chess [1], and I'd love to see rts games played by 'Centaur' teams. In the same way the innovations made in F1 often trickle down to consumer cars, can you imagine the advances that could be made in human-machine interactions in the crucible of a real-time Centaur gaming league? [1] h…

If they allowed you to script micro unit behavior in some way that'd be first step in a hybrid game.

It would also be cool if it was an upgrade you unlock. So, instead of just stat upgrades, you could also purchase AI upgrades.

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

#162

Post by rlayton2 » Fri, Nov 04, 2016, 10:04 PM UTC

lordnacho wrote: post #139

arcticfox wrote: post #134

Earlier quoted context omitted.

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.

> 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?

Infinite micro? I'd just send all drones/probes/SCVs directly to the human's base and kill their drones. The extra drones that the human has wouldn't be able to make up the difference.

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

#163

Post by detaro » Fri, Nov 04, 2016, 10:07 PM UTC

defen wrote: post #159

trjordan wrote: post #154

Earlier quoted context omitted.

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.

How does the AI "know" which Zergling is going to be fired upon? Are the tank shots not instant-hit? Or is this just a demonstration of what actual optimal control would look like.

The tanks aren't given overriding manual commands, so it likely could just predict how their automatic targeting works. If a player would give commands, it could get at least some information from the animation frames before the target is aquired and the shot fired.

(The implementation in the video likely just cheats and gets the information from the engine, but at least the first case should be deterministic enough)

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

#164

Post by thesimpsons1022 » Fri, Nov 04, 2016, 10:09 PM UTC

lordnacho wrote: post #139

arcticfox wrote: post #134

Earlier quoted context omitted.

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.

> 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?

still a tough question but they could do some insane things. for instance if they had 200 marines and controlled each individually i can't imagine what they'd do. for humans it's requires insane mechanics to even break them up into 8 seperatel groups and control them for more than a few seconds

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

#165

Post by xg15 » Fri, Nov 04, 2016, 10:09 PM UTC

I applaud the idea, but I'm worried about how open the results of the research will be in the end.

I think the worst possible outcome for society would be if we ended up with capable AI but with the algorithms only accessible for a handful "AI-as-a-service" companies.

The second concern is understandability of the algorithms: from what I've read, it's already hard to deduce "why" an ANN in a traditional problem behaved like it did. An AI that is capable of coping with dynamic, unpredictable situations like an SC game (with only pixels as input) is impressive but it seems less useful to me if it's not understood how that is done.

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

#166

Post by make3 » Fri, Nov 04, 2016, 10:10 PM UTC

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.

the article says explicitly that they will limit the capacities of the ai to things that are mechanically (physically) possible for humans

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

#167

Post by thesimpsons1022 » Fri, Nov 04, 2016, 10:10 PM UTC

burke wrote: post #148

scarmig wrote: post #137

Earlier quoted context omitted.

Isn't it easy to account for this? Just force the AI to stick to between 100 and 150 APM, and it becomes its responsibility budget its APM.

Sure, but even then it's difficult. Micro'ing three fronts at once would be difficult for a human but could easily fit within the AI's budget. You could solve this by coming up with some sort of context-switch effort function but it starts to feel forced. Or at least, once you start calibrating the parameters of the problem around human limitations, it sort of feels weird to talk about the computer being better or wo…

no one is even mentioning the role of vision in the game. for a human it's pretty tough to keep track of the minimap and play at the same time. you end up missing a lot of things. imagine something that could monitor both simulataneously.

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

#168

Post by mememachine » Fri, Nov 04, 2016, 10:12 PM UTC

xg15 wrote: post #165

I applaud the idea, but I'm worried about how open the results of the research will be in the end. I think the worst possible outcome for society would be if we ended up with capable AI but with the algorithms only accessible for a handful "AI-as-a-service" companies. The second concern is understandability of the algorithms: from what I've read, it's already hard to deduce "why" an ANN in a traditional problem behav…

Well unfortunately im fairly certain that outcome is the source of funding for these research projects, and i dont think socialized funding could hold a match to it nor potentially even provide as much value

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

#169

Post by make3 » Fri, Nov 04, 2016, 10:14 PM UTC

hooloovoo_zoo wrote: post #161

bradleyjg wrote: post #100

Earlier quoted context omitted.

If they allowed you to script micro unit behavior in some way that'd be first step in a hybrid game.

It would also be cool if it was an upgrade you unlock. So, instead of just stat upgrades, you could also purchase AI upgrades.

I'm sure in the next decade we will see the start of modern ai in video games & all ai applied to all kinds of gameplay mechanics, like this one

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

#170

Post by wingcommander » Fri, Nov 04, 2016, 10:16 PM UTC

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…

There is so much sensationalist nonsense by clueless people here, it is insane. Do you freak out over everything you do not understand?

Because you don't understand the solid state physics of your iPhone CPU, does that mean it is magic?

Because you do not understand what a neural network is, does that mean it is magic? NO, it is essentially curve fitting with gradient descent. (Me: PhD in Statistics).