Tingting Ni

Tingting Ni

PhD researcher @ EPFL

Biography

I am a PhD student at EPFL in the Systems Control and Multiagent Optimization Laboratory, supervised by Professor Maryam Kamgarpour. My research focuses on the theoretical foundations of online safe reinforcement learning and multi-agent systems, with broader interests at the intersection of optimization, game theory, and machine learning.

Prior to my PhD, I obtained an MSc in Mathematics from EPFL (2022), where I completed my master’s thesis at the Numerical Algorithms and High-Performance Computing Laboratory under the supervision of Professor Daniel Kressner. I also hold a BSc in Mathematics from Lanzhou University (2020), where I completed my bachelor’s thesis at the Algorithms of Machine Learning and Autonomous Driving Research Laboratory under the supervision of Professor Yang Xiang.

Robotics Projects

Selected robotics projects I supervised: Robotics Projects.

Publications

You can also find my articles on my Google Scholar profile.

Preprints

  1. Tingting Ni, and Maryam Kamgarpour, “Constrained meta reinforcement learning with provable test-time safety,” arXiv:2601.21845,2026

  2. Tingting Ni*, Anna Maddu*, Maryam Kamgarpour, “On characterization and existence of a constrained correlated equilibria in Markov games,” arXiv:2507.03502, 2025.

Journal Papers

  1. Daniel Kressner*, Tingting Ni*, and André Uschmajew*, “On the approximation of vector-valued functions by volume sampling,” Journal of Complexity, 2025.

Conference Papers

  1. Tingting Ni, and Maryam Kamgarpour, “A learning-based approach to stochastic optimal control under reach-avoid constraint,” In Proceedings of the 28th ACM International Conference on Hybrid Systems: Computation and Control (HSCC), 2025.
  2. Tingting Ni, and Maryam Kamgarpour, “A safe exploration approach to constrained Markov decision processes,” In International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR, 2025. (Presented also at ICML 2024 Workshop: Foundations of Reinforcement Learning and Control)
  3. Fateme Baneshi, Marıa Cerezo Magana, Manuel Soler, Tingting Ni, and Maryam Kamgarpour, “Aircraft trajectory planning for climate hotspot avoidance considering air traffic complexity: A constrained multi-agent reinforcement learning approach,” In SESAR Innovation Days, 2024.
  4. Titouan Renard*, Andreas Schlaginhaufen*, Tingting Ni*, Maryam Kamgarpour, “Convergence of a model-free entropy-regularized inverse reinforcement learning algorithm,” In 63rd IEEE Conference on Decision and Control (CDC), 2024.