# Scalable and Reliable Multi-agent Reinforcement Learning for Traffic Assignment

arXiv: https://arxiv.org/abs/2506.17029 · HTML: https://mlsanity.com/paper/2506.17029/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 38 references that are in the map.
- First posted on arXiv 20 Jun 2025.

## Builds on (most cited first, 12 of 12)

- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Bag of Freebies for Training Object Detection Neural Networks](https://mlsanity.com/paper/1902.04103/) (2019)
- [End-to-End Heterogeneous Graph Neural Networks for Traffic Assignment](https://mlsanity.com/paper/2310.13193/) (2023)
- [AI-Driven Day-to-Day Route Choice](https://mlsanity.com/paper/2412.03338/) (2024)
- [Data-Driven Traffic Assignment: A Novel Approach for Learning Traffic Flow Patterns Using a Graph Convolutional Neural Network](https://mlsanity.com/paper/2202.10508/) (2022)
- [Multi-Agent Reinforcement Learning for Markov Routing Games: A New Modeling Paradigm For Dynamic Traffic Assignment](https://mlsanity.com/paper/2011.10915/) (2020)
- [Multi-Class Traffic Assignment using Multi-View Heterogeneous Graph Attention Networks](https://mlsanity.com/paper/2501.09117/) (2025)
- [The Braess Paradox in Dynamic Traffic](https://mlsanity.com/paper/2203.03726/) (2022)
- [Heterogeneous Graph Sequence Neural Networks for Dynamic Traffic Assignment](https://mlsanity.com/paper/2408.04131/) (2024)
- [Reinforcement Learning-based Sequential Route Recommendation for System-Optimal Traffic Assignment](https://mlsanity.com/paper/2505.20889/) (2025)

## Built on by (most cited first, 2 of 2)

- [Network-Constrained Policy Optimization for Adaptive Multi-agent Vehicle Routing](https://mlsanity.com/paper/2510.26089/) (2025)
- [Group Effect Enhanced Generative Adversarial Imitation Learning for Individual Travel Behavior Modeling under Incentives](https://mlsanity.com/paper/2509.06656/) (2025)

## Abstract (arXiv)

The evolution of metropolitan cities and the increase in travel demands impose stringent requirements on traffic assignment methods. Multi-agent reinforcement learning (MARL) approaches outperform traditional methods in modeling adaptive routing behavior without requiring explicit system dynamics, which is beneficial for real-world deployment. However, MARL frameworks face challenges in scalability and reliability when managing extensive networks with substantial travel demand, which limiting their practical applicability in solving large-scale traffic assignment problems. To address these challenges, this study introduces MARL-OD-DA, a new MARL framework for the traffic assignment problem, which redefines agents as origin-destination (OD) pair routers rather than individual travelers, significantly enhancing scalability. Additionally, a Dirichlet-based action space with action pruning and a reward function based on the local relative gap are designed to enhance solution reliability and improve convergence efficiency. Experiments demonstrate that the proposed MARL framework effectively handles medium-sized networks with extensive and varied city-level OD demand, surpassing existing MARL methods. When implemented in the SiouxFalls network, MARL-OD-DA achieves better assignment solutions in 10 steps, with a relative gap that is 94.99% lower than that of conventional methods.