Linear graph-kernel models beat GNNs for learned planning heuristics, and ranking objectives beat cost-to-go regression.
General policies, subgoal structure, and planning width
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Graph Learning for Planning: The Story Thus Far and Open Challenges
Linear graph-kernel models beat GNNs for learned planning heuristics, and ranking objectives beat cost-to-go regression.