While the encoder–decoder structure is widely used in the recent neural construction
methods for learning to solve vehicle routing problems (VRPs), they are less effective in …

Existing neural heuristics often train a deep architecture from scratch for each specific
vehicle routing problem (VRP), ignoring the transferable knowledge across different VRP …

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 …

Neural construction models have shown promising performance for Vehicle Routing
Problems (VRPs) by adopting either the Autoregressive (AR) or Non-Autoregressive (NAR) …

Machine learning has been adapted to help solve NP-hard combinatorial optimization
problems. One prevalent way is learning to construct solutions by deep neural networks …

Recently, Transformer has become a prevailing deep architecture for solving vehicle routing
problems (VRPs). However, it is less effective in learning improvement models for VRP …

We present a novel deep reinforcement learning method to learn construction heuristics for
vehicle routing problems. In specific, we propose a Multi-Decoder Attention Model (MDAM) …

Recently, neural heuristics based on deep learning have reported encouraging results for
solving vehicle routing problems (VRPs), especially on independent and identically …

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 …

Recent neural methods for vehicle routing problems always train and test the deep models
on the same instance distribution (ie, uniform). To tackle the consequent cross-distribution …