‹ back to 2026-08-20

The HydroGym reinforcement learning platform for fluid dynamics

Nature Reinforcement Learning Christian Lagemann, Sajeda Mokbel, Miro Gondrum, Mario Rüttgers, Yuning Wang, Pol Suárez, Ludger Paehler, Deniz A. Bezgin, Aaron B. Buhendwa, Jared L. Callaham, Samuel Ahnert, Nicholas Zolman, Xiao Shao, Jean-Christophe Loiseau, Nikolaus A. Adams, Matthias Meinke, Wolfgang Schröder, Kai Lagemann, Esther Lagemann, Ricardo Vinuesa, Steven L. Brunton 2026-08-19

TL;DR - HydroGym is a standardized platform with more than 60 reinforcement-learning environments for fluid-flow control. It demonstrates that learned control can transfer zero-shot to a 3D wing, reducing local skin friction by 38% while cutting exploration costs by four orders of magnitude.

Provides a common benchmark suite for reinforcement-learning-based flow control.
Includes over 60 standardized fluid-dynamics environments.
Demonstrates zero-shot policy transfer to a 3D wing.
Reports substantially lower exploration costs alongside a 38% local skin-friction reduction.

view merged work →