Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer

by   Yining Ma, et al.
National University of Singapore
Nanyang Technological University
The Hong Kong University of Science and Technology

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 because its positional encoding (PE) method is not suitable in representing VRP solutions. This paper presents a novel Dual-Aspect Collaborative Transformer (DACT) to learn embeddings for the node and positional features separately, instead of fusing them together as done in existing ones, so as to avoid potential noises and incompatible correlations. Moreover, the positional features are embedded through a novel cyclic positional encoding (CPE) method to allow Transformer to effectively capture the circularity and symmetry of VRP solutions (i.e., cyclic sequences). We train DACT using Proximal Policy Optimization and design a curriculum learning strategy for better sample efficiency. We apply DACT to solve the traveling salesman problem (TSP) and capacitated vehicle routing problem (CVRP). Results show that our DACT outperforms existing Transformer based improvement models, and exhibits much better generalization performance across different problem sizes on synthetic and benchmark instances, respectively.


page 6

page 7

page 8

page 9

page 11

page 12

page 14

page 17


A Deep Reinforcement Learning Algorithm Using Dynamic Attention Model for Vehicle Routing Problems

Recent researches show that machine learning has the potential to learn ...

Multi-Decoder Attention Model with Embedding Glimpse for Solving Vehicle Routing Problems

We present a novel deep reinforcement learning method to learn construct...

Generalized Nested Rollout Policy Adaptation with Dynamic Bias for Vehicle Routing

In this paper we present an extension of the Nested Rollout Policy Adapt...

Towards Generalizable Neural Solvers for Vehicle Routing Problems via Ensemble with Transferrable Local Policy

Machine learning has been adapted to help solve NP-hard combinatorial op...

Learning Collaborative Policies to Solve NP-hard Routing Problems

Recently, deep reinforcement learning (DRL) frameworks have shown potent...

Towards Omni-generalizable Neural Methods for Vehicle Routing Problems

Learning heuristics for vehicle routing problems (VRPs) has gained much ...

Complexity-based partitioning of CSFI problem instances with Transformers

In this paper, we propose a two-steps approach to partition instances of...

Code Repositories


This repo implements our paper, "Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer", which has been accepted at NeurIPS 2021.

view repo

Please sign up or login with your details

Forgot password? Click here to reset