Learning Awareness Models

Understand

We consider the setting of an agent with a fixed body interacting with an unknown and uncertain external world.

• We show that models trained to predict proprioceptive information about the agent's body come to represent objects in the external world.
• In spite of being trained with only internally available signals, these dynamic body models come to represent external objects through the necessity of predicting their effects on the agent's own body.
• That is, the model learns holistic persistent representations of objects in the world, even though the only training signals are body signals.