Deep reinforcement learning in fluid mechanics: A promising method for both active flow control and shape optimization

• Published in: Journal of hydrodynamics. Series B 2020-04, Vol.32 (2), p.234-246
• Main Authors: Rabault, Jean, Ren, Feng, Zhang, Wei, Tang, Hui, Xu, Hui
• Format: Article
• Language: English
• Subjects: Engineering; Engineering Fluid Dynamics; Hydrology/Water Resources; Numerical and Computational Physics; Simulation; Special Column on the International Symposium on High-Fidelity Computational Methods and Applications 2019 (Guest Editors Hui Xu; Wei Zhang
• ISSN: 1001-6058; 1878-0342
• DOI: 10.1007/s42241-020-0028-y

In recent years, artificial neural networks (ANNs) and deep learning have become increasingly popular across a wide range of scientific and technical fields, including fluid mechanics. While it will take time to fully grasp the potentialities as well as the limitations of these methods, evidence is starting to accumulate that point to their potential in helping solve problems for which no theoretically optimal solution method is known. This is particularly true in fluid mechanics, where problems involving optimal control and optimal design are involved. Indeed, such problems are famously difficult to solve effectively with traditional methods due to the combination of non linearity, non convexity, and high dimensionality they involve. By contrast, deep reinforcement learning (DRL), a method of optimization based on teaching empirical strategies to an ANN through trial and error, is well adapted to solving such problems. In this short review, we offer an insight into the current state of the art of the use of DRL within fluid mechanics, focusing on control and optimal design problems.