AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
1–10 of 459 posts
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#2They really should have used BroodWar for deep mind. SCII is way too volatile. Way more gimmicks available that will make it difficult for AI to come close to a human player.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#3How did they make those data visualizations? (specifically, the visually-skewed ridge plots). That's a nice approach for those types of plots since they can get cluttered without the perceptual skew.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#4They really should have used BroodWar for deep mind. SCII is way too volatile. Way more gimmicks available that will make it difficult for AI to come close to a human player.
Why? They won ten out of eleven matches. Seems like they got pretty close to human players...
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#5They really should have used BroodWar for deep mind. SCII is way too volatile. Way more gimmicks available that will make it difficult for AI to come close to a human player.
Isn't the difficulty of the task the point? If it was easy it wouldn't be interesting.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#6So... I’m curious how long this will be before we can apply this to real life?
At this point it seems like it’d be fairly complicated, but you could build a solid simulator for battles. Then direct humans and / or robots around the battle field as nessecary to win a battle.
Upload a virtual map utilizing some point clouds, estimate densities, start with estimating enemy combatants, add some scoring metrics negatively impacting civilian deaths and probably a lot of other stuff. Run real life scenarios in training environments, and bam.
The premise seems there.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#7How did they make those data visualizations? (specifically, the visually-skewed ridge plots). That's a nice approach for those types of plots since they can get cluttered without the perceptual skew.
https://seaborn.pydata.org/examples/kde_ridgeplot.html
I would try with a Seaborn facet grid? I think they’ve got something custom, but this should get close (be aware this specific example is a kde so it will normalize total area)
On a second glance this won’t get the 3D horizontal offset.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#8AlphaStar interacted with the StarCraft game engine directly via its raw interface, meaning that it could observe the attributes of its own and its opponent’s visible units on the map directly, without having to move the camera - effectively playing with a zoomed out view of the game
Additionally, and subsequent to the matches, we developed a second version of AlphaStar. Like human players, this version of AlphaStar chooses when and where to move the camera, its perception is restricted to on-screen information, and action locations are restricted to its viewable region.
I was really curious whether they would attempt moving the camera like a human. Sounds like it's still a work in progress, but very exciting! Even this isn't enough to make it fully like a human player, as I believe it is still getting numerical values for unit properties rather than having to infer them from the pixels on the screen. But it seems possible to fix that, likely at the cost of drastically increasing the training time.
The benefit of using pixels, of course, would be that the agent would become fully general. It would probably immediately work on Command & Conquer, for instance, while the current version would require deep integration with the game engine first. But I think the training time would be impractically long.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#9I would really like to see this for Age of Empires II. I think AOE has far more races and is a far more complex game ( although I'm biased because I haven't played SC2 as much as AOEII ).
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#10They really should have used BroodWar for deep mind. SCII is way too volatile. Way more gimmicks available that will make it difficult for AI to come close to a human player.
Why? They won ten out of eleven matches. Seems like they got pretty close to human players...
The games it won, it had an access to inputs human players physically can't do (controlling units off-screen without panning the camera first), so I'm hesitant to call the victories legitimate.
Edit: And reviewing the game it lost, the decision making was questionable at best.