A differentiable neural model recovers ground-truth lifted action schemas from state traces by jointly learning schemas and inferring unobserved action arguments.
McDermott , title =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Algorithms and completeness results for learning equivalent STRIPS+ domains from traces under three partial-observability cases for states while assuming selected action arguments are fully observed.
citing papers explorer
-
Differentiable Learning of Lifted Action Schemas for Classical Planning
A differentiable neural model recovers ground-truth lifted action schemas from state traces by jointly learning schemas and inferring unobserved action arguments.
-
Learning Lifted Action Models from Traces with Minimal Information About Actions and States
Algorithms and completeness results for learning equivalent STRIPS+ domains from traces under three partial-observability cases for states while assuming selected action arguments are fully observed.