AMLE graph value extensions meet a local action-gap certificate guaranteeing goal-reaching greedy rollouts under argmin-Q planning and achieve 0.97 success on AntMaze-derived graphs versus 0.58 for harmonic extension.
Jeff Calder and Dejan Slepčev
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
The paper proposes using Balanced Forman Curvature for coreset selection and dynamic exploration-exploitation switching in graph active learning, combined with localized rewiring, to outperform baselines at low label rates.
citing papers explorer
-
Planner-Admissible Graph-PDE Value Extensions for Sparse Goal-Conditioned Planning
AMLE graph value extensions meet a local action-gap certificate guaranteeing goal-reaching greedy rollouts under argmin-Q planning and achieve 0.97 success on AntMaze-derived graphs versus 0.58 for harmonic extension.
-
Topology-Aware Active Learning on Graphs
The paper proposes using Balanced Forman Curvature for coreset selection and dynamic exploration-exploitation switching in graph active learning, combined with localized rewiring, to outperform baselines at low label rates.