%0 Conference Paper
%A Lagemann, Christian
%A Rüttgers, Mario
%A Gondrum, Miro
%A Meinke, Matthias
%A Schröder, Wolfgang
%A Lintermann, Andreas
%A Brunton, Steven L.
%T Hydro Gym-GPU: From 2D to 3D Benchmark Environments for Reinforcement Learning in Fluid Flows
%V 69
%C Jülich
%I Forschungszentrum Jülich GmbH Zentralbibliothek, Verlag
%M FZJ-2025-02455
%B Schriften des Forschungszentrums Jülich IAS Series
%P 57-63
%D 2025
%< Proceedings of the 35th Parallel CFD International Conference 2024
%X Fluid flow modeling and control is a significant modern challenge with potential impacts across science, technology, and industry. Improved flow control could enhance drag reduction, mixing, and noise reduction in areas like transportation, energy, and medicine. However, progress in flow control is currently hindered by the lack of systematically standardized benchmarks and the high computational cost of fluid simulations. While two-dimensional problems have been extensivelystudied, three-dimensional simulations with larger meshes are rarely considered due to the need forhighly parallelized and specialized solvers. As a result, the engineering burden of encapsulating thesesimulations in benchmark environments has proven to be a significant barrier. In this paper, a GPU-based extension of the HydroGym platform coupling the multiphysics solver framework m-AIA witha state-of-the-art reinforcement learning platform is presented for fluid flow control problems. Basedon the highly-parallelized lattice Boltzmann solver, which is part of m-AIA, a new set of three-dimensional, non-differentiable fluid flow environments is added that extend existing flow controlchallenges to a new level of physical and computational complexity.
%B 35th Parallel CFD International Conference 2024
%C 2 Sep 2024 - 4 Sep 2024, Bonn (Germany)
Y2 2 Sep 2024 - 4 Sep 2024
M2 Bonn, Germany
%F PUB:(DE-HGF)8 ; PUB:(DE-HGF)7
%9 Contribution to a conference proceedingsContribution to a book
%R 10.34734/FZJ-2025-02455
%U https://juser.fz-juelich.de/record/1041823