Zoltán Varga

List of main publications and preprints

1. SoftwareX

   RouteRL: Multi-agent reinforcement learning framework for urban route choice with autonomous vehicles

   Akman, Ahmet Onur, Psarou, Anastasia, Gorczyca, Łukasz, Varga, Zoltán György, Jamróz, Grzegorz, and Kucharski, Rafał

   SoftwareX 2025

   Abs HTML

   RouteRL is a novel framework that integrates multi-agent reinforcement learning (MARL) with a microscopic traffic simulation for the development of efficient collective route choice strategies for autonomous vehicles (AVs). The proposed framework models the daily urban route choices of driver agents of two types: human drivers, emulated using behavioral route choice models, and AVs, modeled as MARL agents optimizing their policies for a predefined objective. RouteRL aims to advance research in MARL, transport modeling, and human–AI interaction for transportation applications. This study presents a technical report on RouteRL, outlines its potential research contributions, and showcases its impact via illustrative examples. Initial findings show that human travel times could increase following the introduction of AVs in urban environments, highlighting the importance of future studies to support efficient urban mobility.

2. Sci. Rep.

   Social implications of coexistence of CAVs and human drivers in the context of route choice

   Jamróz, Grzegorz, Akman, Ahmet Onur, Psarou, Anastasia, Varga, Zoltán György, and Kucharski, Rafał

   Scientific Reports 2025

   Abs HTML

   Suppose in a stable urban traffic system populated only by human driven vehicles (HDVs), a given proportion (e.g. 10 %) is replaced by a fleet of Connected and Autonomous Vehicles (CAVs), which share information and pursue a collective goal. Suppose these vehicles are centrally coordinated and differ from HDVs only by their collective capacities allowing them to make more efficient routing decisions before the travel on a given day begins. Suppose there is a choice between two routes and every day each driver makes a decision which route to take. Human drivers maximize their utility. CAVs might optimize different goals, such as the total travel time of the fleet. We show that in this plausible futuristic setting, the strategy CAVs are allowed to adopt may result in human drivers either benefitting or being systematically disadvantaged and urban networks becoming more or less optimal. Consequently, some regulatory measures might become indispensable.

3. arXiv

   Impact of collective behaviors of autonomous vehicles on urban traffic dynamics: A multi-agent reinforcement learning approach

   Akman, Ahmet Onur, Psarou, Anastasia, Varga, Zoltán György, Jamróz, Grzegorz, and Kucharski, Rafał

   arXiv preprint arXiv:2509.22216 2025

   Abs HTML

   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.

4. arXiv

   Autonomous Vehicles Using Multi-Agent Reinforcement Learning for Routing Decisions Can Harm Urban Traffic

   Psarou, Anastasia, Akman, Ahmet Onur, Gorczyca, Łukasz, Hoffmann, Michał, Varga, Zoltán György, Jamróz, Grzegorz, and Kucharski, Rafał

   arXiv preprint arXiv:2502.13188 2025

   Abs HTML

   Autonomous vehicles (AVs) using Multi-Agent Reinforcement Learning (MARL) for simultaneous route optimization may destabilize traffic environments, with human drivers possibly experiencing longer travel times. We study this interaction by simulating human drivers and AVs. Our experiments with standard MARL algorithms reveal that, even in trivial cases, policies often fail to converge to an optimal solution or require long training periods. The problem is amplified by the fact that we cannot rely entirely on simulated training, as there are no accurate models of human routing behavior. At the same time, real-world training in cities risks destabilizing urban traffic systems, increasing externalities, such as CO2 emissions, and introducing non-stationarity as human drivers adapt unpredictably to AV behaviors. Centralization can improve convergence in some cases, however, it raises privacy concerns for the travelers’ destination data. In this position paper, we argue that future research must prioritize realistic benchmarks, cautious deployment strategies, and tools for monitoring and regulating AV routing behaviors to ensure sustainable and equitable urban mobility systems.