000280953 001__ 280953
000280953 005__ 20250918102643.0
000280953 037__ $$aDZNE-2025-01035
000280953 1001_ $$0P:(DE-HGF)0$$aLagemann, Christian$$b0
000280953 1112_ $$a7th Annual Learning for Dynamics and Control Conference$$cAnn Arbor, MI$$d2025-06-04 - 2025-06-06$$gL4DC 2025$$wUSA
000280953 245__ $$aHydroGym: A Reinforcement Learning Platform for Fluid Dynamics
000280953 260__ $$bML Research Press$$c2025
000280953 29510 $$aProceedings of the 7th Annual Learning for Dynamics & Control Conference
000280953 300__ $$a497 - 512
000280953 3367_ $$2ORCID$$aCONFERENCE_PAPER
000280953 3367_ $$033$$2EndNote$$aConference Paper
000280953 3367_ $$2BibTeX$$aINPROCEEDINGS
000280953 3367_ $$2DRIVER$$aconferenceObject
000280953 3367_ $$2DataCite$$aOutput Types/Conference Paper
000280953 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1758104734_31854
000280953 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb
000280953 4900_ $$v283
000280953 520__ $$aThe modeling and control of fluid flows remain a significant challenge with tremendous potential to advance fields including transportation, energy, and medicine. Effective fluid flow control can lead to drag reduction, enhanced mixing, and noise reduction, among other applications. While reinforcement learning (RL) has shown great success in complex domains, such as robotics and protein folding, its application to flow control is hindered by the lack of standardized platforms and the computational demands of fluid simulations. To address these challenges, we introduce HydroGym, a solver-independent RL platform for flow control research. HydroGym integrates sophisticated flow control benchmarks, a scalable runtime, and state-of-the-art RL algorithms. Our platform includes four validated non-differentiable fluid flow environments and one differentiable environment, all evaluated with a variety of modern RL algorithms. HydroGym’s scalable design allows computations to run seamlessly from laptops to high-performance computing resources, providing a standardized interface for implementing new flow environments. HydroGym aims to bridge the gap in flow control research, providing a robust platform to support both non-differentiable and differentiable RL techniques, fostering advancements in scientific machine learning.
000280953 536__ $$0G:(DE-HGF)POF4-354$$a354 - Disease Prevention and Healthy Aging (POF4-354)$$cPOF4-354$$fPOF IV$$x0
000280953 7001_ $$0P:(DE-HGF)0$$aPaehler, Ludger$$b1
000280953 7001_ $$0P:(DE-HGF)0$$aCallaham, Jared$$b2
000280953 7001_ $$0P:(DE-HGF)0$$aMokbel, Sajeda$$b3
000280953 7001_ $$0P:(DE-HGF)0$$aAhnert, Samuel$$b4
000280953 7001_ $$0P:(DE-2719)9001044$$aLagemann, Kai$$b5$$udzne
000280953 7001_ $$0P:(DE-HGF)0$$aLagemann, Esther$$b6
000280953 7001_ $$0P:(DE-HGF)0$$aAdams, Nikolaus A.$$b7
000280953 7001_ $$0P:(DE-HGF)0$$aBrunton, Steven L.$$b8
000280953 8564_ $$uhttps://proceedings.mlr.press/v283/lagemann25a.html
000280953 8564_ $$uhttps://pub.dzne.de/record/280953/files/DZNE-2025-01035_Restricted.pdf
000280953 8564_ $$uhttps://pub.dzne.de/record/280953/files/DZNE-2025-01035_Restricted.pdf?subformat=pdfa$$xpdfa
000280953 909CO $$ooai:pub.dzne.de:280953$$pVDB
000280953 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)9001044$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b5$$kDZNE
000280953 9131_ $$0G:(DE-HGF)POF4-354$$1G:(DE-HGF)POF4-350$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lNeurodegenerative Diseases$$vDisease Prevention and Healthy Aging$$x0
000280953 9141_ $$y2025
000280953 9201_ $$0I:(DE-2719)1013030$$kAG Mukherjee$$lStatistics and Machine Learning$$x0
000280953 980__ $$acontrib
000280953 980__ $$aVDB
000280953 980__ $$acontb
000280953 980__ $$aI:(DE-2719)1013030
000280953 980__ $$aUNRESTRICTED