A factorized USD framework that mixes METRA and DIAYN per state factor, adds symmetry and style priors, and achieves sim-to-real transfer on a quadruped.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Divide, Discover, Deploy: Factorized Skill Learning with Symmetry and Style Priors
A factorized USD framework that mixes METRA and DIAYN per state factor, adds symmetry and style priors, and achieves sim-to-real transfer on a quadruped.