Learning to Act by Predicting the Future

Alexey Dosovitskiy, Vladlen Koltun

Nov 04, 2016 (modified: Feb 14, 2017) ICLR 2017 conference submission readers: everyone
  • Abstract: We present an approach to sensorimotor control in immersive environments. Our approach utilizes a high-dimensional sensory stream and a lower-dimensional measurement stream. The cotemporal structure of these streams provides a rich supervisory signal, which enables training a sensorimotor control model by interacting with the environment. The model is trained using supervised learning techniques, but without extraneous supervision. It learns to act based on raw sensory input from a complex three-dimensional environment. The presented formulation enables learning without a fixed goal at training time, and pursuing dynamically changing goals at test time. We conduct extensive experiments in three-dimensional simulations based on the classical first-person game Doom. The results demonstrate that the presented approach outperforms sophisticated prior formulations, particularly on challenging tasks. The results also show that trained models successfully generalize across environments and goals. A model trained using the presented approach won the Full Deathmatch track of the Visual Doom AI Competition, which was held in previously unseen environments.
  • TL;DR: We present an approach to sensorimotor control in immersive environments.
  • Conflicts: intel.com, cs.uni-freiburg.de, stanford.edu
  • Authorids: adosovitskiy@gmail.com, vkoltun@gmail.com

Loading