HydroGym: A Reinforcement Learning Platform for Fluid Dynamics

Christian Lagemann, Ludger Paehler, Jared Callaham, Sajeda Mokbel, Samuel Ahnert, Kai Lagemann, Esther Lagemann, Nikolaus Adams, Steven Brunton
Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, PMLR 283:497-512, 2025.

Abstract

The modeling and control of fluid flows remain a significant challenge with tremendous potential to advance fields including transportation, energy, and medicine. Effective fluid flow control can lead to drag reduction, enhanced mixing, and noise reduction, among other applications. While reinforcement learning (RL) has shown great success in complex domains, such as robotics and protein folding, its application to flow control is hindered by the lack of standardized platforms and the computational demands of fluid simulations. To address these challenges, we introduce HydroGym, a solver-independent RL platform for flow control research. HydroGym integrates sophisticated flow control benchmarks, a scalable runtime, and state-of-the-art RL algorithms. Our platform includes four validated non-differentiable fluid flow environments and one differentiable environment, all evaluated with a variety of modern RL algorithms. HydroGym’s scalable design allows computations to run seamlessly from laptops to high-performance computing resources, providing a standardized interface for implementing new flow environments. HydroGym aims to bridge the gap in flow control research, providing a robust platform to support both non-differentiable and differentiable RL techniques, fostering advancements in scientific machine learning.

Cite this Paper

BibTeX
@InProceedings{pmlr-v283-lagemann25a, title = {HydroGym: A Reinforcement Learning Platform for Fluid Dynamics}, author = {Lagemann, Christian and Paehler, Ludger and Callaham, Jared and Mokbel, Sajeda and Ahnert, Samuel and Lagemann, Kai and Lagemann, Esther and Adams, Nikolaus and Brunton, Steven}, booktitle = {Proceedings of the 7th Annual Learning for Dynamics \& Control Conference}, pages = {497--512}, year = {2025}, editor = {Ozay, Necmiye and Balzano, Laura and Panagou, Dimitra and Abate, Alessandro}, volume = {283}, series = {Proceedings of Machine Learning Research}, month = {04--06 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v283/main/assets/lagemann25a/lagemann25a.pdf}, url = {https://proceedings.mlr.press/v283/lagemann25a.html}, abstract = {The modeling and control of fluid flows remain a significant challenge with tremendous potential to advance fields including transportation, energy, and medicine. Effective fluid flow control can lead to drag reduction, enhanced mixing, and noise reduction, among other applications. While reinforcement learning (RL) has shown great success in complex domains, such as robotics and protein folding, its application to flow control is hindered by the lack of standardized platforms and the computational demands of fluid simulations. To address these challenges, we introduce HydroGym, a solver-independent RL platform for flow control research. HydroGym integrates sophisticated flow control benchmarks, a scalable runtime, and state-of-the-art RL algorithms. Our platform includes four validated non-differentiable fluid flow environments and one differentiable environment, all evaluated with a variety of modern RL algorithms. HydroGym’s scalable design allows computations to run seamlessly from laptops to high-performance computing resources, providing a standardized interface for implementing new flow environments. HydroGym aims to bridge the gap in flow control research, providing a robust platform to support both non-differentiable and differentiable RL techniques, fostering advancements in scientific machine learning.} }
Endnote
%0 Conference Paper %T HydroGym: A Reinforcement Learning Platform for Fluid Dynamics %A Christian Lagemann %A Ludger Paehler %A Jared Callaham %A Sajeda Mokbel %A Samuel Ahnert %A Kai Lagemann %A Esther Lagemann %A Nikolaus Adams %A Steven Brunton %B Proceedings of the 7th Annual Learning for Dynamics \& Control Conference %C Proceedings of Machine Learning Research %D 2025 %E Necmiye Ozay %E Laura Balzano %E Dimitra Panagou %E Alessandro Abate %F pmlr-v283-lagemann25a %I PMLR %P 497--512 %U https://proceedings.mlr.press/v283/lagemann25a.html %V 283 %X The modeling and control of fluid flows remain a significant challenge with tremendous potential to advance fields including transportation, energy, and medicine. Effective fluid flow control can lead to drag reduction, enhanced mixing, and noise reduction, among other applications. While reinforcement learning (RL) has shown great success in complex domains, such as robotics and protein folding, its application to flow control is hindered by the lack of standardized platforms and the computational demands of fluid simulations. To address these challenges, we introduce HydroGym, a solver-independent RL platform for flow control research. HydroGym integrates sophisticated flow control benchmarks, a scalable runtime, and state-of-the-art RL algorithms. Our platform includes four validated non-differentiable fluid flow environments and one differentiable environment, all evaluated with a variety of modern RL algorithms. HydroGym’s scalable design allows computations to run seamlessly from laptops to high-performance computing resources, providing a standardized interface for implementing new flow environments. HydroGym aims to bridge the gap in flow control research, providing a robust platform to support both non-differentiable and differentiable RL techniques, fostering advancements in scientific machine learning.
APA
Lagemann, C., Paehler, L., Callaham, J., Mokbel, S., Ahnert, S., Lagemann, K., Lagemann, E., Adams, N. & Brunton, S.. (2025). HydroGym: A Reinforcement Learning Platform for Fluid Dynamics. Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, in Proceedings of Machine Learning Research 283:497-512 Available from https://proceedings.mlr.press/v283/lagemann25a.html.

Related Material