Our group advances mathematical theory and algorithms for decision-making in interactive dynamic environments. To this end, we develop safe learning, stochastic control, distributed control, inverse control and reinforcement learning, multiagent learning and mechanism design. The selected publications and presentations below are a sample of our research results. For full list, please see my Google Scholar.
- Tutorial on learning equilibria in multiagent systems, presented at Informed AI Summer School, UK, 2025
- Tutorial on incorporating safety in reinforcement learning, presented at Control Theory and Reinforcement Learning: Connections and Challenges, Netherlands, 2025
- Plenary talk in ”European Control Conference”, 2024
- A summary of work on learning in games, presented in ”Alpine Game Theory Symposium”, 2023
- A summary of work on stochastic control, presented in ”Nordic Congress of Mathematicians”, 2023
S13. A. Schlaginhaufen, R. Ouhamma and M. Kamgarpour, Efficient Preference-Based Reinforcement Learning: Randomized Exploration Meets Experimental Design, Neural Information Processing Systems (NeurIPS), 2025
S12. K. Ren, C. Chen, H. Sung, H. Ahn, I. M. Mitchell and M. Kamgarpour, Recursively Feasible Chance-Constrained Model Predictive Control Under Gaussian Mixture Model Uncertainty, IEEE Transactions on Control Systems Technology, 2025
S11. S. Hosseinirad, G. Salizzoni, A. A. Porzani and M. Kamgarpour, On Linear Quadratic Potential Games, to appear in Automatica, 2025
S10. T. Ni and M. Kamgarpour, A learning-based approach to stochastic optimal control under reach-avoid constraint, Proceedings of the 28th ACM International Conference on Hybrid Systems: Computation and Control (HSCC), 2025
S9. A. M. Maddux and M. Kamgarpour, Multi-Agent Learning in Contextual Games under Unknown Constraints, International Conference on Artificial Intelligence and Statistics (AISTATS), 2024
S8. Identifiability and Generalizability in Constrained Inverse Reinforcement Learning, Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30224-30251, 2023
S7. I. Usmanova, Y. As, M. Kamgarpour and A. Krause, Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning, Journal of Machine Learning Research, 25(171):1-54, 2024
S6. P. G. Sessa, I. Bogunovic, A. Krause and M. Kamgarpour, Contextual Games: Multiagent Learning with Side Information, Neural Information Processing Systems (NeurIPS), 2020
S5. T. Tatarenko and M. Kamgarpour, Learning Generalized Nash Equilibria in a Class of Convex Games, IEEE Transactions on Automatic Control, 64(4):1426-1439, 2019
S4. O. Karaca, P. G. Sessa, N. Walton and M. Kamgarpour, Designing Coalition-Proof Mechanisms for Auctions over Continuous Goods, IEEE Transactions on Automatic Control, 64(11):4803-4810, 2019
S3. L. Furieri, Y. Zheng, A. Papachristodoulou and M. Kamgarpour, Sparsity Invariance for Convex Design of Distributed Controllers, IEEE Transactions on Control of Network Systems, 2019
S2. O. Karaca*, B. Guo*, T. H. Summers and M. Kamgarpour, Actuator Placement under Structural Controllability using Forward and Reverse Greedy Algorithms, IEEE Transactions on Automatic Control, 2021, to appear, *: equal contribution
S1. P. G. Sessa, D. Frick, T. A. Wood and M. Kamgarpour, From Uncertainty Data to Robust Policies for Temporal Logic Planning, Hybrid Systems: Computation and Control, ACM Lecture Notes in Computer Science, pp.157-166, 2018
The public Github of our lab with code repositories for our papers and certain student project.