Hello there! My name is Onur, I’m a Computer Engineer with a specialization in Artificial Intelligence. I am from a lovely city called Eskişehir in Türkiye. My journey in this field began at Yıldız Technical University in Istanbul, where I earned my Bachelor’s degree in Computer Engineering. For my thesis, I worked on an exciting medical AI project that leveraged computer vision. After completing my Bachelor’s degree, I spent two years in Italy, pursuing a master’s degree in Computer Engineering from the University of Padova.
During my time at UNIPD, I specialized in AI & Robotics and focused my research on Natural Language Processing. My thesis involved proposing a novel static word embedding model. Outside of work, I am passionate about traveling and learning about different culinary practices. Currently, I am thrilled to be a member of the COeXISTENCE team here at Jagiellonian University in the beautiful city of Kraków. Here I continue my learning journey and contribute to building a deeper understanding of the interaction between humans and autonomous agents in future traffic environments.
In today’s fast-changing world of AI, the interactions of various subfields are not just beneficial, but essential. Consequently, I believe that every AI enthusiast is responsible for staying up-to-date with every other subfield, regardless of the specific professional focus. With this mindset, my previous research interests and projects span deep learning, classifiers and regressors, computer vision, clustering algorithms, reinforcement learning, and natural language processing. Also, I have experience with mobile development and The Robotic Operating System. Currently, I am continuing my studies on reinforcement learning. I am exploring innovative methods to model learning in simulations that mirror natural learning processes, aiming for accuracy and efficiency.
List of main publications and preprints
-
URB - Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles
Akman, Ahmet Onur,
Psarou, Anastasia,
Hoffmann, Michał,
Gorczyca, Łukasz,
Kowalski, Łukasz,
Gora, Paweł,
Jamróz, Grzegorz,
and Kucharski, Rafał
arXiv preprint arXiv:2505.17734
2025
Connected Autonomous Vehicles (CAVs) promise to reduce congestion in future urban networks, potentially by optimizing their routing decisions. Unlike for human drivers, these decisions can be made with collective, data-driven policies, developed by machine learning algorithms. Reinforcement learning (RL) can facilitate the development of such collective routing strategies, yet standardized and realistic benchmarks are missing. To that end, we present \our: Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles. \our is a comprehensive benchmarking environment that unifies evaluation across 29 real-world traffic networks paired with realistic demand patterns. \our comes with a catalog of predefined tasks, four state-of-the-art multi-agent RL (MARL) algorithm implementations, three baseline methods, domain-specific performance metrics, and a modular configuration scheme. Our results suggest that, despite the lengthy and costly training, state-of-the-art MARL algorithms rarely outperformed humans. Experimental results reported in this paper initiate the first leaderboard for MARL in large-scale urban routing optimization and reveal that current approaches struggle to scale, emphasizing the urgent need for advancements in this domain.
-
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
arXiv preprint arXiv:2502.20065
2025
RouteRL is a novel framework that integrates multi-agent reinforcement learning (MARL) with a microscopic traffic simulation, facilitating the testing and development of efficient route choice strategies for autonomous vehicles (AVs). The proposed framework simulates the daily route choices of driver agents in a city, including 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.
