Time Reversal as Self-Supervision

Understand

A longstanding challenge in robot learning for manipulation tasks has been the ability to generalize to varying initial conditions, diverse objects, and changing objectives.

• Learning based approaches have shown promise in producing robust policies, but require heavy supervision to efficiently learn precise control, especially from visual inputs.
• We propose a novel self-supervision technique that uses time-reversal to learn goals and provide a high level plan to reach them.
• In particular, we introduce the time-reversal model (TRM), a self-supervised model which explores outward from a set of goal states and learns to predict these trajectories in reverse.