Also these wins are not using same inputs that human receive (ie on screen image) and outputs that humans are allowed. They instead use PySC APIs which has much more flexibility, perfect information and no constraints of limited screen real estate and pixels. There is a claim in that article that they have another version being trained that uses on screen only information but I still don’t know if AI is allowed to bypass the physical constraints of controller. So if AI has access to super human controller you will see AI performing super human actions like many commentators have described here.
Perfect information is a bit of a stretch. There was still fog of war. The AI just played as if the portion of the map visible and actionable at any point in time was the whole map. They retrained with a restriction to a given locus of attention that can change, akin to a screen the player is looking at and acting on.
