# Graph Neural Network Reinforcement Learning for Autonomous Mobility-on-Demand Systems

arXiv: https://arxiv.org/abs/2104.11434 · HTML: https://mlsanity.com/paper/2104.11434/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 26 references that are in the map.
- First posted on arXiv 23 Apr 2021.

## Builds on (most cited first, 11 of 11)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Geometric deep learning: going beyond Euclidean data](https://mlsanity.com/paper/1611.08097/) (2016)
- [A Deterministic Linear Program Solver in Current Matrix Multiplication Time](https://mlsanity.com/paper/1910.11957/) (2019)
- [Deep Reinforcement Learning for Multi-Driver Vehicle Dispatching and Repositioning Problem](https://mlsanity.com/paper/1911.11260/) (2019)
- [Control of Robotic Mobility-On-Demand Systems: a Queueing-Theoretical Perspective](https://mlsanity.com/paper/1404.4391/) (2014)
- [Data-Driven Model Predictive Control of Autonomous Mobility-on-Demand Systems](https://mlsanity.com/paper/1709.07032/) (2017)
- [Model Predictive Control of Autonomous Mobility-on-Demand Systems](https://mlsanity.com/paper/1509.03985/) (2015)
- [Estimating Latent Demand of Shared Mobility through Censored Gaussian Processes](https://mlsanity.com/paper/2001.07402/) (2020)

## Built on by (most cited first, 28 of 28)

- [Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks](https://mlsanity.com/paper/2108.01176/) (2021)
- [Graph Neural Networks in IoT: A Survey](https://mlsanity.com/paper/2203.15935/) (2022)
- [Hybrid Multi-agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems](https://mlsanity.com/paper/2212.07313/) (2022)
- [Learning-based Online Optimization for Autonomous Mobility-on-Demand Fleet Control](https://mlsanity.com/paper/2302.03963/) (2023)
- [Graph Reinforcement Learning for Network Control via Bi-Level Optimization](https://mlsanity.com/paper/2305.09129/) (2023)
- [Robust Electric Vehicle Balancing of Autonomous Mobility-On-Demand System: A Multi-Agent Reinforcement Learning Approach](https://mlsanity.com/paper/2307.16228/) (2023)
- [Risk-Sensitive Soft Actor-Critic for Robust Deep Reinforcement Learning under Distribution Shifts](https://mlsanity.com/paper/2402.09992/) (2024)
- [Offline Hierarchical Reinforcement Learning via Inverse Optimization](https://mlsanity.com/paper/2410.07933/) (2024)
- [Multi-Agent Soft Actor-Critic with Coordinated Loss for Autonomous Mobility-on-Demand Fleet Control](https://mlsanity.com/paper/2404.06975/) (2024)
- [Robo-taxi Fleet Coordination at Scale via Reinforcement Learning](https://mlsanity.com/paper/2504.06125/) (2025)
- [Graph Attention Multi-Agent Fleet Autonomy for Advanced Air Mobility](https://mlsanity.com/paper/2302.07337/) (2023)
- [Learning to Control Autonomous Fleets from Observation via Offline Reinforcement Learning](https://mlsanity.com/paper/2302.14833/) (2023)
- [Evading Community Detection via Counterfactual Neighborhood Search](https://mlsanity.com/paper/2310.08909/) (2023)
- [Real-time Control of Electric Autonomous Mobility-on-Demand Systems via Graph Reinforcement Learning](https://mlsanity.com/paper/2311.05780/) (2023)
- [Subequivariant Reinforcement Learning Framework for Coordinated Motion Control](https://mlsanity.com/paper/2403.15100/) (2024)
- [Metalearning traffic assignment for network disruptions with graph convolutional neural networks](https://mlsanity.com/paper/2603.06763/) (2026)
- [Foresight of Graph Reinforcement Learning Latent Permutations Learnt by Gumbel Sinkhorn Network](https://mlsanity.com/paper/2110.12144/) (2021)
- [Hierarchically Structured Scheduling and Execution of Tasks in a Multi-Agent Environment](https://mlsanity.com/paper/2203.03021/) (2022)
- [Dealing with Sparse Rewards Using Graph Neural Networks](https://mlsanity.com/paper/2203.13424/) (2022)
- [Robust Reinforcement Learning on Graphs for Logistics optimization](https://mlsanity.com/paper/2205.12888/) (2022)
- [Efficient entity-based reinforcement learning](https://mlsanity.com/paper/2206.02855/) (2022)
- [Towards More Efficient Shared Autonomous Mobility: A Learning-Based Fleet Repositioning Approach](https://mlsanity.com/paper/2210.08659/) (2022)
- [The logic of rational graph neural networks](https://mlsanity.com/paper/2310.13139/) (2023)
- [Scalable Ride-Sourcing Vehicle Rebalancing with Service Accessibility Guarantee: A Constrained Mean-Field Reinforcement Learning Approach](https://mlsanity.com/paper/2503.24183/) (2025)
- [A Universal Approach to Feature Representation in Dynamic Task Assignment Problems](https://mlsanity.com/paper/2507.03579/) (2025)
- [GRAND: Guidance, Rebalancing, and Assignment for Networked Dispatch in Multi-Agent Path Finding](https://mlsanity.com/paper/2512.03194/) (2025)
- [Competitive Multi-Operator Reinforcement Learning for Joint Pricing and Fleet Rebalancing in AMoD Systems](https://mlsanity.com/paper/2603.05000/) (2026)
- [Continual Graph Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2610.10302/) (2026)

## Abstract (arXiv)

Autonomous mobility-on-demand (AMoD) systems represent a rapidly developing mode of transportation wherein travel requests are dynamically handled by a coordinated fleet of robotic, self-driving vehicles. Given a graph representation of the transportation network - one where, for example, nodes represent areas of the city, and edges the connectivity between them - we argue that the AMoD control problem is naturally cast as a node-wise decision-making problem. In this paper, we propose a deep reinforcement learning framework to control the rebalancing of AMoD systems through graph neural networks. Crucially, we demonstrate that graph neural networks enable reinforcement learning agents to recover behavior policies that are significantly more transferable, generalizable, and scalable than policies learned through other approaches. Empirically, we show how the learned policies exhibit promising zero-shot transfer capabilities when faced with critical portability tasks such as inter-city generalization, service area expansion, and adaptation to potentially complex urban topologies.