A graph neural network with axial attention learns admissible cost partitions for planning heuristics by predicting weights that satisfy partition constraints by construction via Lagrangian dual equivalence.
Title resolution pending
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
-
Learning Admissible Heuristics via Cost Partitioning
A graph neural network with axial attention learns admissible cost partitions for planning heuristics by predicting weights that satisfy partition constraints by construction via Lagrangian dual equivalence.