Neural combinatorial optimization with heavy decoder: Toward large scale generalization

F Luo, X Lin, F Liu, Q Zhang… - Advances in Neural …, 2023 - proceedings.neurips.cc
Neural combinatorial optimization (NCO) is a promising learning-based approach for solving
challenging combinatorial optimization problems without specialized algorithm design by …

Towards omni-generalizable neural methods for vehicle routing problems

J Zhou, Y Wu, W Song, Z Cao… - … Conference on Machine …, 2023 - proceedings.mlr.press
Learning heuristics for vehicle routing problems (VRPs) has gained much attention due to
the less reliance on hand-crafted rules. However, existing methods are typically trained and …

DeepACO: neural-enhanced ant systems for combinatorial optimization

H Ye, J Wang, Z Cao, H Liang… - Advances in Neural …, 2024 - proceedings.neurips.cc
Abstract Ant Colony Optimization (ACO) is a meta-heuristic algorithm that has been
successfully applied to various Combinatorial Optimization Problems (COPs). Traditionally …

Deep policy dynamic programming for vehicle routing problems

W Kool, H van Hoof, J Gromicho, M Welling - International conference on …, 2022 - Springer
Routing problems are a class of combinatorial problems with many practical applications.
Recently, end-to-end deep learning methods have been proposed to learn approximate …

Learning to delegate for large-scale vehicle routing

S Li, Z Yan, C Wu - Advances in Neural Information …, 2021 - proceedings.neurips.cc
Vehicle routing problems (VRPs) form a class of combinatorial problems with wide practical
applications. While previous heuristic or learning-based works achieve decent solutions on …

Operational Research: methods and applications

F Petropoulos, G Laporte, E Aktas… - Journal of the …, 2024 - Taylor & Francis
Abstract Throughout its history, Operational Research has evolved to include methods,
models and algorithms that have been applied to a wide range of contexts. This …

Learning to search feasible and infeasible regions of routing problems with flexible neural k-opt

Y Ma, Z Cao, YM Chee - Advances in Neural Information …, 2024 - proceedings.neurips.cc
In this paper, we present Neural k-Opt (NeuOpt), a novel learning-to-search (L2S) solver for
routing problems. It learns to perform flexible k-opt exchanges based on a tailored action …

Winner takes it all: Training performant RL populations for combinatorial optimization

N Grinsztajn, D Furelos-Blanco… - Advances in …, 2023 - proceedings.neurips.cc
Applying reinforcement learning (RL) to combinatorial optimization problems is attractive as
it removes the need for expert knowledge or pre-solved instances. However, it is unrealistic …

Simulation-guided beam search for neural combinatorial optimization

J Choo, YD Kwon, J Kim, J Jae… - Advances in …, 2022 - proceedings.neurips.cc
Neural approaches for combinatorial optimization (CO) equip a learning mechanism to
discover powerful heuristics for solving complex real-world problems. While neural …

Ensemble-based deep reinforcement learning for vehicle routing problems under distribution shift

Y Jiang, Z Cao, Y Wu, W Song… - Advances in Neural …, 2024 - proceedings.neurips.cc
While performing favourably on the independent and identically distributed (iid) instances,
most of the existing neural methods for vehicle routing problems (VRPs) struggle to …