cs.ROcs.AI

Conditional Neural Processes for Self-Supervised Goal Discovery in Action Imitation

📅 👥 4 authors arXiv:2610.32688v1

Authors

Abstract

Inspired by infants' ability to learn novel tasks by imitating others, in this work we evaluate to what extent Conditional Neural Processes can autonomously learn representations of actions that are informative about their underlying goal. We show that the addition of an attention mechanism in the hidden space fosters the emergence of robust goal representations early on in the observation of an action sequence, making it a promising model for a robotic self-supervised general learner.

Paper Information

arXiv ID:
2610.32688v1
Published:

Related Categories

cs.ROcs.AI