great they opened it up. I'm sure reinforcement learning / Deep learning will solve this. It has been a tough problem before, but honestly doesnt seem that tough compared to all the harder AI problems.
DeepMind and Blizzard Open StarCraft II as an AI Research Environment
11–20 of 283 posts
Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment
#12Any predictions for how long it will take for an AI to win against the world's best player?
AI can already win against the world's best player now. It's just a question of whether they can win with human-level micro.
There isn't any SC2 AI that's anywhere near as good as a player in an actual game. Sure, they can demonstrate some sick unit control, but that alone isn't enough to win games.
Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment
#13Earlier quoted context omitted.
AI can already win against the world's best player now. It's just a question of whether they can win with human-level micro.
Do you have a citation? As far as I know, existing AIs do not stand much of a chance again humans [1]. My understanding is that even if AIs can beat humans is small skirmishes due to superior micro, they lose so badly at macro that it simply doesn't matter. [1] http://spectrum.ieee.org/automaton/robotics/artificial-intel...
Yeah, you're right. Not sure what the guy is talking about.
Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment
#14When Watson won at Jeopardy, one of its prime advantages was the faster reaction time at pushing the buzzer. The fairness of that has already been hashed out elsewhere, but..... We already know that computers can have superior micro and beat humans at Starcraft through that(1). Is DeepMind going to win by giving themselves a micro advantage that is beyond what reasonable humans can do? (1) https://www.youtube.com/wat…
My understanding is that in a full match, AIs still have no hope against humans, since even though they can crush humans at micro, their macro is still abysmal [1]. I'm not aware of a match where any AI has beat a pro human player at Starcraft -- I'd be interested in learning otherwise!
[1] http://spectrum.ieee.org/automaton/robotics/artificial-intel...
Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment
#15When Watson won at Jeopardy, one of its prime advantages was the faster reaction time at pushing the buzzer. The fairness of that has already been hashed out elsewhere, but..... We already know that computers can have superior micro and beat humans at Starcraft through that(1). Is DeepMind going to win by giving themselves a micro advantage that is beyond what reasonable humans can do? (1) https://www.youtube.com/wat…
My understanding is that in a full match, AIs still have no hope against humans, since even though they can crush humans at micro, their macro is still abysmal [1]. I'm not aware of a match where any AI has beat a pro human player at Starcraft -- I'd be interested in learning otherwise! [1] http://spectrum.ieee.org/automaton/robotics/artificial-intel...
would you love to be proven wrong?
Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment
#16When Watson won at Jeopardy, one of its prime advantages was the faster reaction time at pushing the buzzer. The fairness of that has already been hashed out elsewhere, but..... We already know that computers can have superior micro and beat humans at Starcraft through that(1). Is DeepMind going to win by giving themselves a micro advantage that is beyond what reasonable humans can do? (1) https://www.youtube.com/wat…
Thanks for that video. That's exactly what I hope to see. AI vs. AI with insane micro capabilities. I want to see SC2 played as close to a "perfect" game as possible.
Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment
#17Related: Today I learned that a group of AI researchers has released a paper called: STARDATA: A StarCraft AI Research Dataset. According to one of the authors: "We're releasing a dataset of 65k StarCraft: Brood War games, 1.5b frames, 500m actions, 400GB of data. Check it out!"
> Article: https://arxiv.org/abs/1708.02139
> Github: https://github.com/TorchCraft/StarData
Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment
#18Earlier quoted context omitted.
AI can already win against the world's best player now. It's just a question of whether they can win with human-level micro.
Do you have a citation? As far as I know, existing AIs do not stand much of a chance again humans [1]. My understanding is that even if AIs can beat humans is small skirmishes due to superior micro, they lose so badly at macro that it simply doesn't matter. [1] http://spectrum.ieee.org/automaton/robotics/artificial-intel...
it's not exactly macro.. AI can run perfect macro commands. humans right now have better priority model (in this case, protecting/killing workers) for which the AI in question wasn't trained.
Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment
#19That's surprising. I thought Bliz didn't want anyone near sc2 but approved of sc1 being used for this purpose.
SC1 really doesn't make sense for this, 80% of the skill is just keeping on top of the mindless but mechanically intensive stuff, which is trivial beyond trivial for an AI.
SC2's automated away most of this (pretty much everything but production cycles), which makes it a better measure for AI vs human.
Re: DeepMind and Blizzard Open StarCraft II as an AI Research Environment
#20When Watson won at Jeopardy, one of its prime advantages was the faster reaction time at pushing the buzzer. The fairness of that has already been hashed out elsewhere, but..... We already know that computers can have superior micro and beat humans at Starcraft through that(1). Is DeepMind going to win by giving themselves a micro advantage that is beyond what reasonable humans can do? (1) https://www.youtube.com/wat…
My understanding is that in a full match, AIs still have no hope against humans, since even though they can crush humans at micro, their macro is still abysmal [1]. I'm not aware of a match where any AI has beat a pro human player at Starcraft -- I'd be interested in learning otherwise! [1] http://spectrum.ieee.org/automaton/robotics/artificial-intel...
That's because there hasn't been too much concentrated effort on this problem yet, since you'd have to spend quite a bit of effort just integrating with the game engine.
Certainly a lot less research has been done on computer SC2 than computer go, and nobody expected a pro to be beaten there 1.5 years ago, either.