Team

We are looking for new team members. Please get in touch with us if you are interested in!

Graduate Students

Yüksel Arslantaş

Yüksel received a B.S. degree with a full scholarship from the Department of Electrical and Electronics Engineering at Bilkent University in June 2022. He is currently an M.S. student in the same department. His research interests include (multi-agent) reinforcement learning, control theory, game theory, and robotics. For additional details, please refer to Yüksel’s personal webpage.

Papers:

  • Y. Arslantas, E. Yuceel, and M. O. Sayin, “Strategizing against Q-learners: A control-theoretical approach,” IEEE Control Systems Letters, 2024. [url]
  • Y. Arslantas, A. S. Donmez, E. Yuceel, and M. O. Sayin. Vulnerability assessment of reinforcement learning in stochastic security games, 2024.
  • Y. Arslantas and M. O. Sayin. Strategic control of experience-weighted attraction model in human-AI interactions, 2024.
  • A. S. Donmez, Y. Arslantas, and M. O. Sayin. Team collaboration vs competition: New fictitious play dynamics for multi-team zero-sum games, arXiv:2402.02147, 2024. [url]
  • Y. Arslantas, E. Yuceel, Y. Yalin, and MO. Sayin. Convergence of heterogeneous learning dynamics in zero-sum stochastic games, arXiv:2311.00778, 2023. [url]

Ahmet Said Dönmez

Said received a B.S. degree with a full scholarship and high honors from Bilkent University in June 2023 with a CGPA of 3.96 / 4.00. During his undergraduate years, he won high-achievement scholarships from the Republic of Turkey Prime Ministry and ISBANK. He received the 2nd rank among more than 2 million students in Turkey’s Nationwide University Entrance Examination in 2018. He won a silver medal in the National Mathematical Olympiads of Turkey in 2017. He is currently an M.S. student in the same department. His research interests include signal processing, machine learning, and (multi-agent) reinforcement learning.

Papers:

  • A. S. Donmez and M. O. Sayin, “Generalized individual Q-learning for polymatrix games with partial observations,” in IEEE CDC, 2024.
  • Y. Arslantas, A. S. Donmez, E. Yuceel, and M. O. Sayin. Vulnerability assessment of reinforcement learning in stochastic security games, 2024.
  • A. S. Donmez, Y. Arslantas, and M. O. Sayin. Team collaboration vs competition: New fictitious play dynamics for multi-team zero-sum games, arXiv:2402.02147, 2024. [url]

Şeref Taha Kiremitçi

Taha received a B.S. degree from the Department of Electrical and Electronics Engineering at Bilkent University in June 2023. He is currently an M.S. student in the same department. He is also working as an AI Engineer at a company that conducts R&D on computer vision and autonomous systems. His research interests include multi-agent and risk-aware learning.

Yusuf Saltan

Yusuf received a B.S. degree from the Department of Electrical and Electronics Engineering at Bilkent University in June 2023. He is currently an M.S. student in the same department. His research interests include (multi-agent) reinforcement learning, intelligent transportation systems, and routing games.

Papers:

  • Y. Saltan, A. Kosay, C.-W. Lin, and M. O. Sayin. Strategic control of intersections for efficient traffic routing without tolls, 2024.

Undergraduate Students

Arda Koşay

Arda is an undergraduate student in the Department of Electrical and Electronics Engineering at Bilkent University and is expecting to graduate in June 2025. His research interests include game theory, reinforcement learning, intelligent transportation systems and the development and analysis of simulations for complex systems.

Papers:

  • Y. Saltan, A. Kosay, C.-W. Lin, and M. O. Sayin. Strategic control of intersections for efficient traffic routing without tolls, 2024.

Alumni

Yiğit Yalın

Yiğit received a B.S. degree with a full scholarship and high honors from the Department of Computer Engineering at Bilkent University in June 2024. He moved to Max Plank Institute for a Ph.D. on computer and information science.

Papers:

  • Y. Arslantas, E. Yuceel, Y. Yalin, and MO. Sayin. Convergence of heterogeneous learning dynamics in zero-sum stochastic games, arXiv:2311.00778, 2023. [url]

Ege Yüceel

Ege received a B.S. degree with a full scholarship and high honors from the Department of Electrical and Electronics Engineering at Bilkent University in June 2024. He moved to the Electrical and Computer Engineering Department at the University of Illinois at Urbana-Champaign, IL, for a Ph.D.

Papers:

  • Y. Arslantas, E. Yuceel, and M. O. Sayin, “Strategizing against Q-learners: A control-theoretical approach,” IEEE Control Systems Letters, 2024. [url]
  • Y. Arslantas, A. S. Donmez, E. Yuceel, and M. O. Sayin. Vulnerability assessment of reinforcement learning in stochastic security games, 2024.
  • Y. Arslantas, E. Yuceel, Y. Yalin, and MO. Sayin. Convergence of heterogeneous learning dynamics in zero-sum stochastic games, arXiv:2311.00778, 2023. [url]

Onur Ünlü

Onur received a B.S. degree with a full scholarship and high honors from the Department of Electrical and Electronics Engineering at Bilkent University in June 2023 with a CGPA of 3.97 / 4.00. He moved to the Electrical and Computer Engineering Department at Cornell University, Ithaca, NY, for a Ph.D.

Papers:

  • O. Unlu and M. O. Sayin, “Episodic logit-Q dynamics for efficient learning in stochastic teams,” in IEEE CDC, 2023. [url]
  • M. O. Sayin and O. Unlu. Logit-Q dynamics for efficient learning in stochastic teams, arXiv:2302.09806v2, 2023. [url]