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

181–190 of 344 posts

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

#181

Post by endgame »

chrishare wrote: post #177

Very interesting stuff. Allowing researchers to build AIs that operate on either game state or visual data is a great step, IMO. Being able to limit actions-per-minute is also very wise. The excellent BWAPI library for Starcraft Broodwar that is referenced ( https://github.com/bwapi/bwapi ) provides game state - and was presumably used by Facebook to do their research earlier this year ( http://arxiv.org/abs/1609.029…

I wonder if this would have ever been built or released if bwapi wasn't a thing.

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

#182

Post by empath75 »

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…

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 an invasion without losing any soldiers, war seems like a much less dangerous proposition.

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

#183

Post by nogbit »

TulliusCicero wrote: post #77
stale2002 wrote: post #61

Earlier quoted context omitted.

An apm limit is needed because impossibly high APM results in stupid strategies that the game wasn't designed for. The point is to build ai that compete with humans using human strategies. Not to cheese with borked game mechanic exploits.

In practice right now the AI still loses even with unlimited APM. It's just too dumb to really take advantage of its execution speed.

Buts it's intentionally dumbed down to keep the game fun, loosing all the time would get frustrating real quick. Theres no ROI for AI devs to kick the humans ass (except for maybe now with our AI/Cloud/VR/ craze).

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

#184

Post by mmanfrin »

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

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

#185

Post by catshirt »

rlayton2 wrote: post #162
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?

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.

you are oversimplifying things and ignoring a lot of variables.

just to illustrate a point: on a sufficiently large map, i could have four times as many workers by the time your first set reaches my spawn.

if i'm playing Protoss against a Terran AI, i have an added advantage of worker regen without having to stop attacking.

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

#186

Post by rcthompson »

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…

I think you just need to require the computer to do the same thing a human does and only look at a specific part of the map at a time. Then switching between fronts will require clicking on the minimap to move the view to a different front, so frequent context switching is naturally penalized by the APM limit.

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

#187

Post by qznc »

empath75 wrote: post #182
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…

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.

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

#189

Post by rcthompson »

chc wrote: post #140
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.

APM limiting would be an interesting way to scale the game's difficulty level.

Maybe at high levels of play it would, but limiting the APM to even very low levels (e.g. 60 APM, i.e. 1 action per second) would still allow the computer to macro very efficiently, so I don't think it would be a balanced difficulty adjustment. It would be simulating highly skilled player with limited mobility rather than a player that is overall less skilled.

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

#190

Post by rcthompson »

cmdrfred wrote: post #152
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.

Depends on how you limit as well, what if it does 100 actions at once for example.

I'm guessing that a limit of X actions per minute would be implemented by imposing a delay of 1/X minutes after each action during which the computer cannot execute another action.
Post reply on HN