5 papers
The HydroGym Reinforcement Learning Platform for Fluid Dynamics
Christian Lagemann, Sajeda Mokbel, Miro Gondrum +18
Modeling and controlling fluids is critical across science and engineering. Effective flow control can increase lift, reduce drag, enhance mixing, and attenuate noise, potentially…
Uncovering Extreme Event Mechanisms for Prediction and Control with Sensitivity-Balanced Projections
Nicholas Zolman, Sajeda Mokbel, Samuel E. Otto +1
Extreme events -- such as earthquakes and coronal mass ejections -- are common in many chaotic dynamical systems, yet are difficult to characterize and predict due to the subtle in…
SINDy-KANs: Sparse identification of non-linear dynamics through Kolmogorov-Arnold networks
Amanda A. Howard, Nicholas Zolman, Bruno Jacob +2
Kolmogorov-Arnold networks (KANs) have arisen as a potential way to enhance the interpretability of machine learning. However, solutions learned by KANs are not necessarily interpr…
SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning
Nicholas Zolman, Christian Lagemann, Urban Fasel +2
Deep reinforcement learning (DRL) has shown significant promise for uncovering sophisticated control policies that interact in complex environments, such as stabilizing a tokamak f…
A Unified Framework to Enforce, Discover, and Promote Symmetry in Machine Learning
Samuel E. Otto, Nicholas Zolman, J. Nathan Kutz +1
Symmetry is present throughout nature and continues to play an increasingly central role in physics and machine learning. Fundamental symmetries, such as Poincaré invariance, allo…