Graph Meta-Reinforcement Learning for Transferable Autonomous Mobility-on-Demand

Daniele Gammelli, Kaidi Yang, James Harrison, Filipe M Pereira Duarte Rodrigues, Francisco Camara Pereira, Marco Pavone

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

65 Downloads (Pure)

Abstract

Autonomous Mobility-on-Demand (AMoD) systems represent an attractive alternative to existing transportation paradigms, currently challenged by urbanization and increasing travel needs. By centrally controlling a fleet of self-driving vehicles, these systems provide mobility service to customers and are currently starting to be deployed in a number of cities around the world. Current learning-based approaches for controlling AMoD systems are limited to the single-city scenario, whereby the service operator is allowed to take an unlimited amount of operational decisions within the same transportation system. However, real-world system operators can hardly afford to fully re-train AMoD controllers for every city they operate in, as this could result in a high number of poor-quality decisions during training, making the single-city strategy a potentially impractical solution. To address these limitations, we propose to formalize the multi-city AMoD problem through the lens of meta-reinforcement learning (meta-RL) and devise an actor-critic algorithm based on recurrent graph neural networks. In our approach, AMoD controllers are explicitly trained such that a small amount of experience within a new city will produce good system performance. Empirically, we show how control policies learned through meta-RL are able to achieve near-optimal performance on unseen cities by learning rapidly adaptable policies, thus making them more robust not only to novel environments, but also to distribution shifts common in real-world operations, such as special events, unexpected congestion, and dynamic pricing schemes.
Original languageEnglish
Title of host publicationProceedings of the ACM SIGKDD '22 Conference on Knowledge Discovery and Data Mining
Number of pages18
Publication date2022
Pages20-37
Publication statusPublished - 2022
Event28th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - Washington DC Convention Center, Washington, United States
Duration: 14 Aug 202218 Aug 2022
Conference number: 28
https://kdd.org/kdd2022/

Conference

Conference28th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Number28
LocationWashington DC Convention Center
Country/TerritoryUnited States
CityWashington
Period14/08/202218/08/2022
Internet address

Fingerprint

Dive into the research topics of 'Graph Meta-Reinforcement Learning for Transferable Autonomous Mobility-on-Demand'. Together they form a unique fingerprint.

Cite this