All of these machine learning models, plugged into one another, allow a virtual agent to perceive a game world and play within it properly. But what if you could take a machine down inside of its own dream?

Der Artikel (motherboard.vice) gibt Links zum maschinenlernden VizDoom (worldmodels.github.io, vizdoom.cs.put.edu.pl etc.) preis, wo Forscher ihren Experimente Aufbau und ihre Erfahrungen beschreiben.