IVNTR learns neural predicates from demonstrations for bilevel planning and reaches about 77% success on unseen robot tasks, outperforming prior methods that stay below 35%.
Towards a unified theory of state abstraction for mdps
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.RO 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Bilevel Learning for Bilevel Planning
IVNTR learns neural predicates from demonstrations for bilevel planning and reaches about 77% success on unseen robot tasks, outperforming prior methods that stay below 35%.