I didn't catch if they mentioned this in the interview, but what would have happened if they let AlphaStar play against other races, not Protoss only, would it be completely lost, unable to achieve anything?
AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
11–20 of 459 posts
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#12AlphaStar 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…
yeah I was disappointed to discover it worked this way.
don't get me wrong, it's a major accomplishment in AI regardless, but it's a significant advantage and it would be easier for me to appreciate the AI's skill if I didn't have to keep reminding myself that it can see the whole map at once. it's such an information advantage.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#13The problem is see is the AI is not better than the human, it's just 1000x faster at APM / macro. It could have a "shit" bo and still win because it's so much faster than a human. It's not really interesting tbh.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#14I didn't catch if they mentioned this in the interview, but what would have happened if they let AlphaStar play against other races, not Protoss only, would it be completely lost, unable to achieve anything?
Good question. What's important, I think, is to remember that this is an early iteration, and regardless of what it can do now, they will continue to improve it and in a year or two or three (probably less) it will be able to play totally unfettered in all conditions.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#15They 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.
As much as I love brood war, great micro over a large number of units with wide awareness (things which appear to be easy to AlphaStar) would be ridiculously overpowered, even with completely average strategy. Brood War is an awesome game because it's constantly asking too much of its players at all times. I can't imagine games against an AI which has far more attention and micro to give would be too interesting.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#16I 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 ).
I'm sure that once the dust settles, we will have an AlphaZero version for AlphaStar as well
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#17I 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 ).
Same, totally agreed. I'm a really experienced competitive AoE2 player (not pro, just a serious casual), and I think the long-term planning inherent to AoE is far more complex than SC. Not to mention the procedurally generated maps that are different every game-- it's far more nuanced in my view and requires a truly vast amount of knowledge to make good decisions. There are so many different valid approaches to any given situation.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#18It's amazing what they achieved so far, but I wonder how it would stack up against Serral, who draws a lot of his wins by supremely judging an engagement and continiously gains small advantages over the course of a game. This is a skill even most other professional players only have on a much lower level.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#19They 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.
As much as I love brood war, great micro over a large number of units with wide awareness (things which appear to be easy to AlphaStar) would be ridiculously overpowered, even with completely average strategy. Brood War is an awesome game because it's constantly asking too much of its players at all times. I can't imagine games against an AI which has far more attention and micro to give would be too interesting.
They are planning on limiting the APM of the AI anyway. With BW, you can focus on an AI learning basic strategy with incomplete information. With SC2, you mix in a hole assortment of figuring out how crazy abilities like force fields and recall. It's going to take much longer for an AI to anticipate when its opponent is going to force field the ramp and warp into the main.
Re: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
#20How 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.
A lot of the viz styles seem close to ggplot2 which is why I though it was made using ggridges (https://cran.r-project.org/web/packages/ggridges/vignettes/i...) but I'm not sure if you can do a perceptual skew in ggplot2.