(2) Compositional generalization
(2) Compositional generalization
By supervising with multiple axes, the robot can learn behavior that’s not in the data, e.g. fast behavior for a task that has only slow episodes in the data.
This isn’t possible with traditional reward models.
https://bender.layer3.press/articles/019f364e-d1e1-11e1-71b3-35d33d566852
Write a comment