# Learning from Drivers to Tackle the Amazon Last Mile Routing Research Challenge

arXiv: https://arxiv.org/abs/2205.04001 · HTML: https://mlsanity.com/paper/2205.04001/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 26 references that are in the map.
- First posted on arXiv 9 May 2022.

## Builds on (most cited first, 3 of 3)

- [Attention, Learn to Solve Routing Problems!](https://mlsanity.com/paper/1803.08475/) (2018)
- [The Transformer Network for the Traveling Salesman Problem](https://mlsanity.com/paper/2103.03012/) (2021)
- [Constrained Local Search for Last-Mile Routing](https://mlsanity.com/paper/2112.15192/) (2021)

## Built on by (most cited first, 4 of 4)

- [Inverse Optimization for Routing Problems](https://mlsanity.com/paper/2307.07357/) (2023)
- [Pivoting Retail Supply Chain with Deep Generative Techniques: Taxonomy, Survey and Insights](https://mlsanity.com/paper/2403.00861/) (2024)
- [A Bi-Objective Approach to Last-Mile Delivery Routing Considering Driver Preferences](https://mlsanity.com/paper/2405.16051/) (2024)
- [A zone-based training approach for last-mile routing using Graph Neural Networks and Pointer Networks](https://mlsanity.com/paper/2601.04705/) (2026)

## Abstract (arXiv)

The goal of the Amazon Last Mile Routing Research Challenge is to integrate the real-life experience of Amazon drivers into the solution of optimal route planning and optimization. This paper presents our method that tackles this challenge by hierarchically combining machine learning and conventional Traveling Salesperson Problem (TSP) solvers. Our method reaps the benefits from both worlds. On the one hand, our method encodes driver know-how by learning a sequential probability model from historical routes at the zone level, where each zone contains a few parcel stops. It then uses a single step policy iteration method, known as the Rollout algorithm, to generate plausible zone sequences sampled from the learned probability model. On the other hand, our method utilizes proven methods developed in the rich TSP literature to sequence stops within each zone efficiently. The outcome of such a combination appeared to be promising. Our method obtained an evaluation score of 0.0374, which is comparable to what the top three teams have achieved on the official Challenge leaderboard. Moreover, our learning-based method is applicable to driving routes that may exhibit distinct sequential patterns beyond the scope of this Challenge. The source code of our method is publicly available at https://github.com/aws-samples/amazon-sagemaker-amazon-routing-challenge-sol