I’m a student in the Department of Mathematics at Princeton University. I’m very fortunate to be advised by Prof. Elad Hazan. I am interested in the intersection of reinforcement learning in differentiable, physics-based environments and control. My main focus is theoretical, in that I want to develop algorithms with provable guarantees, but the ultimate goal is for these to also translate to practice, for example, to ensure better/safer control of medical apparatus, or more scalable psychotherapy via RL agents.
Non-Stochastic Control with Bandit Feedback. NeurIPS 2020. With John Hallman, and Elad Hazan.
SyntaxNet for Romanian: Results and Potential. Proceedings of the 12th International Conference Linguistic Resources and Tools for Processing the Romanian Language, 2016. With Radu Ion.
Adaptive Regret for Control of Time-Varying Dynamics. Theoretical Foundations of Reinforcement Learning Workshop, ICML 2020. With Elad Hazan, and Edgar Minasyan.
DELUCA - A Differentiable Control Library: Environments, Methods, and Benchmarking. Differentiable Computer Vision, Graphics, and Physics in Machine Learning Workshop, NeurIPS 2020. With John Hallman, Daniel Suo, Alex Yu, Naman Agarwal, Udaya Ghai, Karan Singh, Cyril Zhang, Anirudha Majumdar, and Elad Hazan.