近日，美国华盛顿大学Brunton, Steven L.团队报道了流体动力学的HydroGym强化学习平台。该项研究成果发表在2026年8月19日出版的《自然》杂志上。

有效控制流体流动在运输、能源和医学等领域至关重要，可以增加升力、减小阻力、增强混合和降低噪声。然而，流体因其高维、非线性和多尺度动力学特性而极难控制，传统方法难以应对这些挑战。强化学习在蛋白质折叠和复杂博弈等领域已取得显著进展，这些领域拥有共享的基准测试和标准化环境。流体动力学领域此前缺乏此类基础设施，因此每个控制器通常针对单一几何构型和运行条件进行调优，导致进展难以积累、迁移和比较。

研究组介绍了HydroGym——一个求解器无关的强化学习平台，提供超过60个经过验证、公开可用的流动控制环境，涵盖从典型层流到复杂湍流的各类流动，雷诺数系统性地从低到高，最高可达Re=4×105，并包含二维和三维的马赫数变化。在这些环境中，智能体反复发现稳健的控制策略，包括边界层操控、声反馈干扰和湍流尾迹重整。关键的是，研究组展示了零样本迁移的概念验证：仅在低成本的替代环境中训练得到的智能体，被成功部署到具有挑战性的实际场景中，例如三维机翼段。

与直接在机翼上优化相比，研究组在将探索成本降低四个数量级的同时，实现了局部表面摩擦减少38%。由于这种迁移利用了近壁面物理的相似性，泛化的广度仍有待探索，这为在计算成本高昂的仿真环境中开展策略泛化研究开辟了新途径。通过为可重复研究提供一个通用且可扩展的基础，HydroGym将流动控制从孤立的个案研究推向协同的社区行动。

附：英文原文

Title: The HydroGym reinforcement learning platform for fluid dynamics

Author: Lagemann, Christian, Mokbel, Sajeda, Gondrum, Miro, Rttgers, Mario, Wang, Yuning, Surez, Pol, Paehler, Ludger, Bezgin, Deniz A., Buhendwa, Aaron B., Callaham, Jared L., Ahnert, Samuel, Zolman, Nicholas, Shao, Xiao, Loiseau, Jean-Christophe, Adams, Nikolaus A., Meinke, Matthias, Schrder, Wolfgang, Lagemann, Kai, Lagemann, Esther, Vinuesa, Ricardo, Brunton, Steven L.

Issue&Volume: 2026-08-19

Abstract: Effective control of fluid flows is critical across transportation, energy and medicine, where it can increase lift, reduce drag, enhance mixing and attenuate noise1,2,3. Yet fluids are notoriously difficult to control because they involve high-dimensional, nonlinear and multiscale dynamics that resist conventional approaches4,5,6. Reinforcement learning has driven remarkable progress in fields such as protein folding and complex games, which have shared benchmarks and standardized environments7,8,9,10. Fluid dynamics has lacked such infrastructure, so each controller is typically tuned to a single geometry and operating condition, making progress difficult to accumulate, transfer and compare11,12,13. Here we introduce HydroGym, a solver-independent reinforcement learning platform providing more than 60 validated, openly available flow control environments spanning from canonical laminar flows to complex turbulent flows, with systematic progression in the Reynolds number up to Re = 4 × 105, and Mach number variations in two and three dimensions. Across these environments, agents repeatedly discover robust control principles, including boundary layer manipulation, disruption of acoustic feedback and reorganization of turbulent wakes. Critically, we demonstrate a proof of concept for zero-shot transfer, in which agents that are trained exclusively in inexpensive surrogate environments are deployed to challenging real-world scenarios such as a three-dimensional wing section. We achieve a 38% reduction in local skin friction while reducing exploration costs by four orders of magnitude compared with direct on-wing optimization. As this transfer exploits shared near-wall physics, the breadth of generalization remains open, suggesting a new pathway for research toward policy generalization across computationally prohibitive simulation environments. By offering a common, extensible foundation for reproducible research, HydroGym moves flow control from isolated case studies toward a cohesive community effort.

DOI: 10.1038/s41586-026-10917-6

Source: https://www.nature.com/articles/s41586-026-10917-6