Introduces MnLP, a training method adding multi-step node prediction supervision to improve neural policies for vehicle routing problems.
INViT: A generalizable routing problem solver with invariant nested view transformer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning with Foresight: Enhancing Neural Routing Policy via Multi-Node Lookahead Prediction
Introduces MnLP, a training method adding multi-step node prediction supervision to improve neural policies for vehicle routing problems.