Reinforcement Learning for Multi-Truck Vehicle Routing Problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Levin, Joshua, Correll, Randall, Ide, Takanori, Suzuki, Takafumi, Takaho, Saito, Arai, Alan
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929649162911744
author Levin, Joshua
Correll, Randall
Ide, Takanori
Suzuki, Takafumi
Takaho, Saito
Arai, Alan
author_facet Levin, Joshua
Correll, Randall
Ide, Takanori
Suzuki, Takafumi
Takaho, Saito
Arai, Alan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2211_17078
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Reinforcement Learning for Multi-Truck Vehicle Routing Problems
Levin, Joshua
Correll, Randall
Ide, Takanori
Suzuki, Takafumi
Takaho, Saito
Arai, Alan
Machine Learning
Artificial Intelligence
Optimization and Control
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.
title Reinforcement Learning for Multi-Truck Vehicle Routing Problems
topic Machine Learning
Artificial Intelligence
Optimization and Control
url https://arxiv.org/abs/2211.17078