Some more clues are leaking out about the description two weeks ago of Google's AlphaStar machine learning system that competes in the video game StarCraft.[1]
A key element may be the mysterious "polytope."
What is a polytope? A Euclidean geometric figure of N dimensions, of which two-dimensional polygons and three-dimensional polyhedra are the familiar examples. The polytope is emerging as a way to think about the landscape of possible solutions in a game such as StarCraft.
Also: Fairness in AI, StarCraft Edition[2]
There's no paper yet for AlphaStar, but following Google's blog post about the program on Jan. 24[3], clues began to emerge.
As mentioned in a separate post last week[4], AlphaStar builds upon work by Google's DeepMind group, specifically researcher David Balduzzi and colleagues, regarding something called "Nash averaging," where multiple computer agents that play the game against one another are surveyed by the neural network across multiple games. That survey finds different attributes that can be combined to create a kind of ideal player built from strengths of various agents in those multiple games. The exploration of players, what's referred to by Balduzzi and colleagues as the "gamescape," is expressed as a polytope.
Now, Google researchers have offered up another examination of the polytope, in a two papers released simultaneously late last week, one building upon the next.