Conditional Neural Processes for Self-Supervised Goal Discovery in Action Imitation
Presented at the poster session of the Workshop on World Models and Predictive Coding in Cognitive Robotics @ IROS2023 (https://world-model.emergent-symbol.systems/)
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.
兴趣：imitation learning and diffusion policies for robot control