A review on deep reinforcement learning for fluid mechanics

DOI10.1016/j.compfluid.2021.104973OpenAlexW2967095864MaRDI QIDQ2245392

Alexander Kuhnle, Aurélien Larcher, Jonathan Viquerat, Paul Garnier, Jean Rabault, Elie Hachem

Publication date: 15 November 2021

Published in: Computers and Fluids (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1908.04127

zbMATH Keywords

fluid mechanicsdeep reinforcement learning

Mathematics Subject Classification ID

Fluid mechanics (76-XX)

Related Items

Comparative analysis of machine learning methods for active flow control, Dynamic metasurface control using deep reinforcement learning, Deep reinforcement learning of viscous incompressible flow, Accelerating high order discontinuous Galerkin solvers using neural networks: 1D Burgers' equation, A deep reinforcement learning framework for dynamic optimization of numerical schemes for compressible flow simulations, StressD: 2D stress estimation using denoising diffusion model, Accelerating high order discontinuous Galerkin solvers using neural networks: 3D compressible Navier-Stokes equations, Near-grazing bifurcations and deep reinforcement learning control of an impact oscillator with elastic constraints, Multi-fidelity reinforcement learning framework for shape optimization, Reinforcement-learning-based control of confined cylinder wakes with stability analyses, Reinforcement-learning-based control of convectively unstable flows, Reinforcement-learning-based actuator selection method for active flow control

Uses Software

• FEniCS
• OpenAI Gym
• GitHub
• Pluribus
• Stable Baselines

Cites Work

• Hybrid method for aerodynamic shape optimization in automotive industry
• Optimally staggered finned circular and elliptic tubes in forced convection
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• On the computational power of neural nets
• An Introduction to Deep Reinforcement Learning
• Optimal rotary control of the cylinder wake using proper orthogonal decomposition reduced-order model
• Multidisciplinary shape optimization in aerodynamics and electromagnetics using genetic algorithms
• An analysis of temporal-difference learning with function approximation
• Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control
• Optimization Methods for Large-Scale Machine Learning
• Control of chaotic systems by deep reinforcement learning
• Superhuman AI for multiplayer poker
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item