VIP learns a visual embedding from human videos whose distance defines dense, smooth rewards for arbitrary goal-image robot tasks without task-specific fine-tuning.
As in R3M’s real-world robot experiment setup, the policy takes in concatenated visual embedding of current observation and robot’s proprioceptive state and outputs robot action
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2022 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training
VIP learns a visual embedding from human videos whose distance defines dense, smooth rewards for arbitrary goal-image robot tasks without task-specific fine-tuning.