SCAL derives an upper bound on target-domain imitation loss using source loss plus state-conditional latent KL divergence and aligns distributions via a discriminator-based adversarial estimator.
Invariance through latent alignment.arXiv preprint arXiv:2106.10863, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
State-Conditional Adversarial Learning: An Off-Policy Visual Domain Transfer Method for End-to-End Imitation Learning
SCAL derives an upper bound on target-domain imitation loss using source loss plus state-conditional latent KL divergence and aligns distributions via a discriminator-based adversarial estimator.