A review on deep reinforcement learning for fluid mechanics

Paul Garnier (1) , Jonathan Viquerat (1) , Jean Rabault (2) , Aurélien Larcher (1) , Alexander Kuhnle (3) , Elie Hachem (1)

1 CEMEF - Centre de Mise en Forme des Matériaux
2 UiO - University of Oslo
3 CAM - University of Cambridge [UK]

Deep reinforcement learning (DRL) has recently been adopted in a wide range of physics and engineering domains for its ability to solve decision-making problems that were previously out of reach due to a combination of non-linearity and high dimensionality. In the last few years, it has spread in the field of computational mechanics, and particularly in fluid dynamics, with recent applications in flow control and shape optimization. In this work, we conduct a detailed review of existing DRL applications to fluid mechanics problems. In addition, we present recent results that further illustrate the potential of DRL in Fluid Mechanics. The coupling methods used in each case are covered, detailing their advantages and limitations. Our review also focuses on the comparison with classical methods for optimal control and optimization. Finally, several test cases * Corresponding author are described that illustrate recent progress made in this field. The goal of this publication is to provide an understanding of DRL capabilities along with state-of-the-art applications in fluid dynamics to researchers wishing to address new problems with these methods.

Domaines: Modélisation et simulation; Intelligence artificielle [cs.AI]

Paul Garnier, Jonathan Viquerat, Jean Rabault, Aurélien Larcher, Alexander Kuhnle, et al.. A review on deep reinforcement learning for fluid mechanics. Computers and Fluids, 2021, 225, pp.104973. ⟨10.1016/j.compfluid.2021.104973⟩. ⟨hal-02401491v2⟩