A video labeling model trained with visual shift contrast, latent future reconstruction, and ground-truth action prediction enables sample-efficient policy cloning from action-free videos on Procgen.
Balancing state exploration and skill diversity in unsupervised skill discovery,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Sample-efficient Unsupervised Policy Cloning from Ensemble Self-supervised Labeled Videos
A video labeling model trained with visual shift contrast, latent future reconstruction, and ground-truth action prediction enables sample-efficient policy cloning from action-free videos on Procgen.