Reinforcement-learned neighborhood operator selection improves variable neighborhood search for vehicle routing with multiple time windows, beating adaptive VNS by 3-15% in route length while running several times faster.
Transportation Science 54, 400–416
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning to Search for Vehicle Routing with Multiple Time Windows
Reinforcement-learned neighborhood operator selection improves variable neighborhood search for vehicle routing with multiple time windows, beating adaptive VNS by 3-15% in route length while running several times faster.