Towards Scalable Three-Dimensional Loading Capacitated Vehicle Routing

Current vehicle routing methods suffer from non-linear scaling with increasing problem size and are therefore bound to limited geographic areas to compute results in time for day-to-day operations. This only allows for local optima in routing and leaves global optimization potential untouched. We develop a reinforcement learning model to approximately solve the three-dimensional loading capacitated vehicle routing problem in linear time. We demonstrate the linear time scaling of our reinforcement learning model and benchmark our routing performance against state-of-the-art methods. Our results show a promising first step towards large-scale logistics optimization with reinforcement learning.