AIDA augments scarce target data for sim-to-real visual RL by adaptively truncating unreliable imagined rollouts via a distribution-shift-aware discriminator and applying self-consistency loss on reliable state reconstructions.
arXiv preprint arXiv:2409.08687 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Domain Adaptation with Adaptive Imagination for Visual Reinforcement Learning under Limited Target Data
AIDA augments scarce target data for sim-to-real visual RL by adaptively truncating unreliable imagined rollouts via a distribution-shift-aware discriminator and applying self-consistency loss on reliable state reconstructions.