27 papers
Shaping Wind-Tunnel Airflow for Unmanned Aerial Vehicles using Online Learning
Ghadeer Elmkaiel, Michael Muehlebach
The development and testing of advanced aerial robots require experiments in controlled environments with tailored airflow profiles. This paper presents an online learning algorith…
Foundations of Reinforcement Learning and Control:Connections and New Perspectives
Claire Vernade, Onno Eberhard, Martha White +4
Reinforcement learning and control theory are two adjacent scientific fields that focus on optimizing the controller of unknown dynamical systems using feedback. While both fields…
Zeroth-Order Optimization at the Edge of Stability
Minhak Song, Liang Zhang, Bingcong Li +3
Zeroth-order (ZO) methods are widely used when gradients are unavailable or prohibitively expensive, including black-box learning and memory-efficient fine-tuning of large models,…
Gray-Box Nonlinear Feedback Optimization
Zhiyu He, Saverio Bolognani, Michael Muehlebach +1
Feedback optimization enables autonomous optimality seeking of a dynamical system through its closed-loop interconnection with iterative optimization algorithms. Among various iter…
Learning Dynamic Swing-Up of an Inverted Pendulum using Remote Magnetic Actuation
Viacheslav Sydora, Jasan Zughaibi, Denis von Arx +2
Electromagnetic Navigation Systems (eMNS) have gained considerable attention for minimally invasive surgery and targeted drug delivery. While most of the literature relies on quasi…
Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via Landing
Kijung Jeon, Michael Muehlebach, Molei Tao
Generative modeling within constrained sets is essential for scientific and engineering applications involving physical, geometric, or safety requirements (e.g., molecular generati…