Reinforcement Learning for Multi-Truck Vehicle Routing Problems
This addresses a real-world industrial-scale supply chain logistics problem for companies like Aisin Corporation, but it is incremental as it builds on existing encoder-decoder attention models.
The paper tackled the complex vehicle routing problem variant with multiple trucks and multi-leg routing requirements by developing new extensions to existing encoder-decoder attention models, and found that their algorithm outperformed the previous best solution in a real supply chain environment for Aisin Corporation.
Deep reinforcement learning (RL) has been shown to be effective in producing approximate solutions to some vehicle routing problems (VRPs), especially when using policies generated by encoder-decoder attention mechanisms. While these techniques have been quite successful for relatively simple problem instances, there are still under-researched and highly complex VRP variants for which no effective RL method has been demonstrated. In this work we focus on one such VRP variant, which contains multiple trucks and multi-leg routing requirements. In these problems, demand is required to move along sequences of nodes, instead of just from a start node to an end node. With the goal of making deep RL a viable strategy for real-world industrial-scale supply chain logistics, we develop new extensions to existing encoder-decoder attention models which allow them to handle multiple trucks and multi-leg routing requirements. Our models have the advantage that they can be trained for a small number of trucks and nodes, and then embedded into a large supply chain to yield solutions for larger numbers of trucks and nodes. We test our approach on a real supply chain environment arising in the operations of Japanese automotive parts manufacturer Aisin Corporation, and find that our algorithm outperforms Aisin's previous best solution.