He focuses on research challenges in socio-technical systems where humans and technological systems can engage with each other. His overarching research goal is to develop an understanding for the theoretical and algorithmic foundation of learning and autonomy in complex and dynamic systems to solve societal challenges with systematic guarantees.
Before moving to Bilkent University, he was a Postdoctoral Associate at the Laboratory for Information and Decision Systems, Massachusetts Institute of Technology from September 2019 to August 2021. He studied the theoretical and algorithmic foundation of multi-agent reinforcement learning with independent and autonomous learners.
He got his Ph.D. from the University of Illinois at Urbana-Champaign, Electrical and Computer Engineering Department in 2019. He studied the theoretical foundation of how intelligent and autonomous decision-makers (including humans or human-like artificial intelligence) would share their strategic information with others in complex and dynamic environments.
During his doctoral studies, he has also conducted research at Toyota Info-Tech Labs, Mountain View CA to develop solutions to practical problems in intelligent transportation systems. His patent on “Managing roadway intersections for vehicles” is granted on Oct. 2021.
He got his M.S. and B.S. degrees from Bilkent University, Electrical and Electronics Engineering Department, respectively, in 2015 and 2013.
The full list of publications is available at Publications.
Detailed information on current and previous research projects can be found at Projects.
- M. O. Sayin and O. Unlu, “Logit-Q learning in Markov games”, available at arXiv:2205.13266. [url]
- M. O. Sayin, K. Zhang, and A. Ozdaglar, “Fictitious play in Markov games with single controller,” in ACM EC, 2022. [url]
- M. O. Sayin, “On the global convergence of stochastic fictitious play in stochastic games with turn-based controllers”, to appear in IEEE CDC’22. [url]
- M. O. Sayin and K. A. Cetiner, “On the heterogeneity of independent learning dynamics in zero-sum stochastic games”, L4DC’22. [pdf][url]
- A. Ozdaglar, M. O. Sayin and K. Zhang, “Independent Learning in Stochastic Games,” available at arXiv:2111.11743, An invited chapter for the International Congress of Mathematicians 2022 (ICM’22). [url]
- M. O. Sayin*, K. Zhang*, D. S. Leslie, T. Başar, and A. Ozdaglar, “Decentralized Q-learning in Zero-sum Markov Games,” in NeurIPS, 2021, available at arXiv:2106.02748. [url][poster]
- M. O. Sayin, F. Parise, and A. Ozdaglar, “Fictitious Play in Zero-sum Stochastic Games,” SIAM J. Cont. Opt., available at arXiv:2010.04223, 2022. [url]
- M. O. Sayin and T. Başar, “Bayesian Persuasion with State-Dependent Quadratic Cost Measures,” IEEE Trans. Automatic Control, 2021. [url]
- M. O. Sayin and T. Başar, “Persuasion-based Robust Sensor Design Against Attackers with Unknown Control Objectives,” IEEE Trans. Automatic Control, 2021. [url]
- M. O. Sayin, et al. Minimax Detection (MAD) for Computer Security: A Dynamic Program Characterization. In Game Theory and Machine Learning for Cyber Security, John Wiley & Sons, 2021. [url]
- M. O. Sayin and T. Başar. Deception-As-Defense Framework for Cyber-Physical Systems. In Safety, Security, and Privacy for Cyber-Physical Systems, Springer, 2021. [url]
- M. O. Sayin, et al., “Reliable Smart Road Signs,” IEEE Trans. Intell. Transp. Syst., 2020. [url]