# Impact of Collective Behaviors of Autonomous Vehicles on Urban Traffic Dynamics: A Multi-Agent Reinforcement Learning Approach

arXiv: https://arxiv.org/abs/2509.22216 · HTML: https://mlsanity.com/paper/2509.22216/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Cooperative and V2X driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 3 of its 18 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Placed in

- End-to-end autonomous driving / [Cooperative and V2X driving](https://mlsanity.com/driving/cooperative-and-v2x-driving/)

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

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Altruistic Autonomy: Beating Congestion on Shared Roads](https://mlsanity.com/paper/1810.11978/) (2018)

## Built on by (most cited first, 1 of 1)

- [Collective Autonomous Vehicle Routing Needs Social Awareness for Coexistence with Human Drivers](https://mlsanity.com/paper/2610.13439/) (2026)

## Abstract (arXiv)

This study examines the potential impact of reinforcement learning (RL)-enabled autonomous vehicles (AV) on urban traffic flow in a mixed traffic environment. We focus on a simplified day-to-day route choice problem in a multi-agent setting. We consider a city network where human drivers travel through their chosen routes to reach their destinations in minimum travel time. Then, we convert one-third of the population into AVs, which are RL agents employing Deep Q-learning algorithm. We define a set of optimization targets, or as we call them behaviors, namely selfish, collaborative, competitive, social, altruistic, and malicious. We impose a selected behavior on AVs through their rewards. We run our simulations using our in-house developed RL framework PARCOUR. Our simulations reveal that AVs optimize their travel times by up to 5%, with varying impacts on human drivers' travel times depending on the AV behavior. In all cases where AVs adopt a self-serving behavior, they achieve shorter travel times than human drivers. Our findings highlight the complexity differences in learning tasks of each target behavior. We demonstrate that the multi-agent RL setting is applicable for collective routing on traffic networks, though their impact on coexisting parties greatly varies with the behaviors adopted.