ISyE Colloquium: Reinforcement Learning for Solving the Vehicle Routing Problem

In this work, we present an end-to-end framework for solving the Vehicle Routing Problem (VRP) using a specially constructed Neural Network (NN) structure and Reinforcement Learning (RL). VRP is a combinatorial optimization problem that has been studied for decades and for which many exact and heuristic algorithms have been proposed, but providing fast and reliable solutions is still a challenging task.