How did Google's DeepMind train AlphaStar to play Starcraft 2 with reinforcement learning and did that mean running the Starcraft game in an accelerated way billions of times to train the neural network?

From AlphaStar: Mastering the Real-Time Strategy Game StarCraft IIAlphaStar's behaviour is generated by a deep neural network that receives input data from the raw game interface (a list of units and their properties), and outputs a sequence of instructions that constitute an action within the game. More specifically, the