Ege Yüceel

Ege Yüceel

PhD Student at University of Illinois Urbana-Champaign

Ege Yüceel

Hi, I’m Ege! I recently graduated with a Bachelor’s in Electrical and Electronics Engineering from Bilkent University. At Bilkent, my research spanned algorithmic game theory, multi-agent learning, and reinforcement learning under the guidance of Dr. Muhammed Sayın in the Games, Decisions, and Networks Lab.

Now, I am working on synthesizing theoretically provable, optimal controllers for autonomous systems operating under partial information while ensuring they meet hard safety constraints under the guidance of Prof. Sayan Mitra at UIUC.

📰 News

  • 🎉 Exciting announcement! I am starting my PhD in Electrical and Computer Engineering at the University of Illinois at Urbana-Champaign (UIUC). I am honored to work under the guidance of Prof. Sayan Mitra.
  • 🎉 Exciting news! Our paper “Strategizing against Q-learners: A Control-theoretical Approach” has been accepted for publication in the prestigious IEEE Control Systems Letters (IEEE L-CSS)!
  • We are delighted to share that the revised version of our preprint ‘Strategizing against Q-learners: A Control-theoretical Approach’ is now available on arXiv! This updated version expands our original research to cover multiplayer game settings. In this iteration, we extend our methodology to scenarios where N-type agents define the game state while A-type agents compete. You can access the updated preprint at arXiv:2403.08906.
  • Our latest preprint, co-authored with Yüksel Arslantaş and Muhammed Ömer Sayın, is now available on arXiv! Titled ‘Strategizing against Q-learners: A Control-theoretical Approach’, you can read it at arXiv:2403.08906.
  • Dr. Sayın recently presented our findings on “Convergence of Heterogeneous Learning Dynamics in Zero-sum Stochastic Games” at the CDC Workshop 2023 on “Control, Game, and Learning Theory for Security and Privacy”.
  • We are excited to announce that our newest preprint, co-authored with Yüksel Arslantaş, Yiğit Yalın, and Muhammed Ömer Sayın, is now live on arXiv! The paper, titled ‘Convergence of Heterogeneous Learning Dynamics in Zero-sum Stochastic Games’, is available for you to read at arXiv:2311.00778.
  • Dr. Sayın delivered an invited talk on “Convergent Heterogeneous Learning for Zero-sum Stochastic Games” at the Annual Allerton Conference, sharing insights from our ongoing research in this domain.