A policy model trained jointly with JEPA-style latent observation-sequence prediction matches ACT baselines in Meta-World and improves a proprioceptive reconstruction probe, though the task-success gain is within error bars.
and Kaiser, Lukasz and Polosukhin, Illia , booktitle =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning
A policy model trained jointly with JEPA-style latent observation-sequence prediction matches ACT baselines in Meta-World and improves a proprioceptive reconstruction probe, though the task-success gain is within error bars.