What Can I Do Here? Learning New Skills by Imagining Visual Affordances

2 code implementations • 1 Jun 2021 • Alexander Khazatsky, Ashvin Nair, Daniel Jing, Sergey Levine

In effect, prior data is used to learn what kinds of outcomes may be possible, such that when the robot encounters an unfamiliar setting, it can sample potential outcomes from its model, attempt to reach them, and thereby update both its skills and its outcome model.

Zero-shot Generalization