POMO+: Leveraging starting nodes in POMO for solving Capacitated Vehicle Routing Problem

TL;DR

This paper introduces POMO+, an improved reinforcement learning method for the Capacitated Vehicle Routing Problem that leverages initial nodes to enhance solution quality and convergence speed.

Contribution

POMO+ enhances the original POMO model by utilizing starting nodes, leading to faster convergence and better solutions for VRP instances.

Findings

Faster convergence of solutions.

Improved results on CVRPLIB dataset.

Effective on instances with up to 100 customers.

Abstract

In recent years, reinforcement learning (RL) methods have emerged as a promising approach for solving combinatorial problems. Among RL-based models, POMO has demonstrated strong performance on a variety of tasks, including variants of the Vehicle Routing Problem (VRP). However, there is room for improvement for these tasks. In this work, we improved POMO, creating a method (\textbf{POMO+}) that leverages the initial nodes to find a solution in a more informed way. We ran experiments on our new model and observed that our solution converges faster and achieves better results. We validated our models on the CVRPLIB dataset and noticed improvements in problem instances with up to 100 customers. We hope that our research in this project can lead to further advancements in the field.