mlsanityData to 14 Oct 2026

Transfer learning-enhanced deep reinforcement learning for aerodynamic airfoil optimisation subject to structural constraints

arXiv 2505.02634 ↗First posted 5 May 2025cs.LG physics.comp-phcited by 4

On the map: Deep reinforcement learning methods → RL with diffusion and flow models

Abstract (arXiv)

The main objective of this paper is to introduce a transfer learning-enhanced deep reinforcement learning (DRL) methodology that is able to optimise the geometry of any airfoil based on concomitant aerodynamic and structural integrity criteria. To showcase the method, we aim to maximise the lift-to-drag ratio CL/CD while preserving the structural integrity of the airfoil -- as modelled by its maximum thickness -- and train the DRL agent using a list of different transfer learning (TL) strategies. The performance of the DRL agent is compared with Particle Swarm Optimisation (PSO), a traditional gradient-free optimisation method. Results indicate that DRL agents are able to perform purely aerodynamic and hybrid aerodynamic/structural shape optimisation, that the DRL approach outperforms PSO in terms of computational efficiency and aerodynamic improvement, and that the TL-enhanced DRL agent achieves performance comparable to the DRL one, while further saving substantial computational resources.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in RL with diffusion and flow models, one of 15 directions in Deep reinforcement learning methods. Builds on 18 of its 51 references that are in the map. First posted on arXiv 5 May 2025.

Builds on

18 of 51 references.

References · 18

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
  4. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  5. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  6. 2017A Brief Survey of Deep Reinforcement Learningcited by 483
  7. 2019Machine Learning for Fluid Mechanicscited by 385
  8. 2021Enhancing Computational Fluid Dynamics with Machine Learningcited by 138
  9. 2019A review on Deep Reinforcement Learning for Fluid Mechanicscited by 66
  10. 2019Direct shape optimization through deep reinforcement learningcited by 28
  11. 2020Data-Driven Aerospace Engineering: Reframing the Industry with Machine Learningcited by 27
  12. 2023The transformative potential of machine learning for experiments in fluid mechanicscited by 27
6 more
  1. 2022Improving aircraft performance using machine learning: a reviewcited by 19
  2. 2025NeuralFoil: An Airfoil Aerodynamics Analysis Tool Using Physics-Informed Machine Learningcited by 11
  3. 2022Multi-fidelity reinforcement learning framework for shape optimizationcited by 9
  4. 2023A reinforcement learning strategy for p-adaptation in high order solverscited by 4
  5. 2024Towards certification: A complete statistical validation pipeline for supervised learning in industrycited by 4
  6. 2024Reinforcement learning for anisotropic p-adaptation and error estimation in high-order solverscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025A Certifiable Machine Learning-Based Pipeline to Predict Fatigue Life of Aircraft Structurescited by 3
  2. 2026FluidFlow: a flow-matching generative model for fluid dynamics surrogates on unstructured meshescited by 3
  3. 2025Reliable Statistical Guarantees for Conformal Predictors with Small Datasetscited by 1
  4. 2026Kolmogorov Arnold networks (KAN) for aerodynamic prediction: a comparison with MLPs and GNNscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A mechanism-driven reinforcement learning framework for shape optimization of airfoils
  2. 2024Enhancing Vehicle Aerodynamics with Deep Reinforcement Learning in Voxelised Models
  3. 2025Reinforcement Learning for Accelerated Aerodynamic Shape Optimisation
  4. 2026High-lift Wing Separation Control via Bayesian Optimization and Deep Reinforcement Learning
  5. 2024Towards Active Flow Control Strategies Through Deep Reinforcement Learning
  6. 2026Co-Design of Aeroelastic Systems with Deep Reinforcement Learning
  7. 2024Model-Based Reinforcement Learning for Control of Strongly-Disturbed Unsteady Aerodynamic Flows
  8. 2026AirfoilGen: A valid-by-construction and performance-aware latent diffusion model for airfoil generation