Video, actions and proprioception

Vector: one demonstration from another scene, level 1

The policy is shown one demonstration of a task - the frames of three cameras, the action trajectory and the proprioception - recorded by RoboTwin's expert in one scene, and must do the task in another scene of the same level. Level 1 varies the objects' positions and yaw between the two. Submissions are weights of the BPP architecture only.

A rollout starts from a different initial state than the demonstration’s, so its actions do not fit and cannot simply be replayed.