mlsanityData to 14 Oct 2026

Reinforcement Learning for Accelerated Aerodynamic Shape Optimisation

arXiv 2507.17786 ↗First posted 23 Jul 2025cs.LGcited by 0

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

Abstract (arXiv)

We introduce a reinforcement learning (RL) based adaptive optimization algorithm for aerodynamic shape optimization focused on dimensionality reduction. The form in which RL is applied here is that of a surrogate-based, actor-critic policy evaluation MCMC approach allowing for temporal 'freezing' of some of the parameters to be optimized. The goals are to minimize computational effort, and to use the observed optimization results for interpretation of the discovered extrema in terms of their role in achieving the desired flow-field. By a sequence of local optimized parameter changes around intermediate CFD simulations acting as ground truth, it is possible to speed up the global optimization if (a) the local neighbourhoods of the parameters in which the changed parameters must reside are sufficiently large to compete with the grid-sized steps and its large number of simulations, and (b) the estimates of the rewards and costs on these neighbourhoods necessary for a good step-wise parameter adaption are sufficiently accurate. We give an example of a simple fluid-dynamical problem on which the method allows interpretation in the sense of a feature importance scoring.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL with diffusion and flow models, one of 15 directions in Deep reinforcement learning methods. Builds on 6 of its 18 references that are in the map. First posted on arXiv 23 Jul 2025.

Builds on

6 of 18 references.

References · 6

  1. 2015Trust Region Policy Optimizationcited by 2,580
  2. 2019A review on Deep Reinforcement Learning for Fluid Mechanicscited by 66
  3. 2019Direct shape optimization through deep reinforcement learningcited by 28
  4. 2020Component-wise reduced order model lattice-type structure designcited by 16
  5. 2020Learning the aerodynamic design of supercritical airfoils through deep reinforcement learningcited by 10
  6. 2022A Neural Network Approach for Homogenization of Multiscale Problemscited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024A mechanism-driven reinforcement learning framework for shape optimization of airfoils
  2. 2025Transfer learning-enhanced deep reinforcement learning for aerodynamic airfoil optimisation subject to structural constraints
  3. 2026Knowledge-Constrained Shape Optimization with a Mixture-of-Experts Neural Operator for High-Confidence Design
  4. 2025Adjoint-Based Aerodynamic Shape Optimization with a Manifold Constraint Learned by Diffusion Models
  5. 2024Model-Based Reinforcement Learning for Control of Strongly-Disturbed Unsteady Aerodynamic Flows
  6. 2026Physics-guided surrogate learning enables zero-shot control of turbulent wings
  7. 2024Enhancing Vehicle Aerodynamics with Deep Reinforcement Learning in Voxelised Models
  8. 2024Generative Aerodynamic Design with Diffusion Probabilistic Models