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

TL;DR

This paper applies deep reinforcement learning with graph models and heterogeneous attention mechanisms to effectively solve the Traveling Salesperson Problem with precedence constraints, demonstrating scalability and adaptability.

Contribution

It generalizes heterogeneous attention mechanisms to TSPPC and incorporates sparsification for improved scalability in DRL solutions.

Findings

Effective DRL-based solutions for TSPPC

Enhanced scalability through attention sparsification

Successful adaptation of recent DRL methods to TSPPC

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 (MHA) 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.