Solving the Traveling Salesperson Problem with Precedence Constraints by Deep Reinforcement Learning

Christian Löwens, Inaam Ashraf, Alexander Gembus, Genesis Cuizon, Jonas K. Falkner, Lars Schmidt-Thieme

Abstract

This work presents solutions to the Traveling Salesperson Problem with precedence constraints (TSPPC) using Deep Reinforcement Learning (DRL) by adapting recent approaches that work well for regular TSPs. Common to these approaches is the use of graph models based on multi-head attention layers. One idea for solving the pickup and delivery problem (PDP) is using heterogeneous attentions to embed the different possible roles each node can take. In this work, we generalize this concept of heterogeneous attentions to the TSPPC. Furthermore, we adapt recent ideas to sparsify attentions for better scalability. Overall, we contribute to the research community through the application and evaluation of recent DRL methods in solving the TSPPC. Our code is available at https://github.com/christianll9/tsppc-drl .
BibTeX
@inproceedings{lowens2022solving,
  author = {Christian Löwens and Inaam Ashraf and Alexander Gembus and Genesis Cuizon and Jonas K. Falkner and Lars Schmidt-Thieme},
  title = {{Solving the Traveling Salesperson Problem with Precedence Constraints by Deep Reinforcement Learning}},
  booktitle = {KI},
  year = {2022},
}
Figure