AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Learning to Plan with Uncertain Topological Maps

Edward Beeching, Jilles Dibangoye, Olivier Simonin, Christian Wolf

ECCV 2020 · Graph learning › Graph algorithms and clustering · approach: Neural combinatorial optimization on graphs · 38 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add visual node features to the neural planner (ablation)neural graph planner · uncertain graphsH-SPL: 0.468 -> 0.501Improved
add visual node features to the neural planner (ablation)neural graph planner · uncertain graphsaccuracy: 0.251 -> 0.262Improved
use neural planner without visual features instead of best symbolic baselineneural graph planner · uncertain graphsH-SPL: 0.269 -> 0.468Improved
add modality mixing (mod-drop with GT adjacency) during training (ablation)neural graph planner · uncertain graphsaccuracy: 2.3% improvementImproved
sample point-goals from planner output instead of argmaxneural planner + local policy · hierarchical navigationSPL: 0.877 -> 0.796Hurt
sample point-goals from planner output instead of argmaxneural planner + local policy · hierarchical navigationsuccess rate: 0.983 -> 0.966Hurt
use neural planner instead of symbolic custom costneural planner + local policy · hierarchical navigationsuccess rate: 0.707 -> 0.983Improved
add GRU for message accumulation (Bellman-Ford bias) to graph network (ablation)neural graph planner · planner accuracy vs data size 8,000 to 74,000 graphsaccuracyImproved
increase local policy steps m up to 20 time-steps (ablation)hierarchical agent · 1,200 validation instancessuccess: 20 time-stepsNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy