mlsanityData to 7 Oct 2026

Direct shape optimization through deep reinforcement learning

arXiv 1908.09885 ↗First posted 23 Aug 2019cs.CEcited by 28

Not on the map. Why?

Abstract (arXiv)

Deep Reinforcement Learning (DRL) has recently spread into a range of domains within physics and engineering, with multiple remarkable achievements. Still, much remains to be explored before the capabilities of these methods are well understood. In this paper, we present the first application of DRL to direct shape optimization. We show that, given adequate reward, an artificial neural network trained through DRL is able to generate optimal shapes on its own, without any prior knowledge and in a constrained time. While we choose here to apply this methodology to aerodynamics, the optimization process itself is agnostic to details of the use case, and thus our work paves the way to new generic shape optimization strategies both in fluid mechanics, and more generally in any domain where a relevant reward function can be defined.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 6; 2023: 4; 2024: 6; 2025: 6; 2026: 3.

28 papers.

Sort:

By area:

  1. 2022Machine Learning in Aerodynamic Shape Optimizationcited by 39
  2. 2021Physics-informed Dyna-Style Model-Based Deep Reinforcement Learning for Dynamic Controlcited by 22
  3. 2022Deep reinforcement learning for optimal well control in subsurface systems with uncertain geologycited by 9
  4. 2022Multi-fidelity reinforcement learning framework for shape optimizationcited by 8
  5. 2023Dynamic Feature-based Deep Reinforcement Learning for Flow Control of Circular Cylinder with Sparse Surface Pressure Sensingcited by 7
  6. 2021Multi-condition multi-objective optimization using deep reinforcement learningcited by 6
  7. 2023Sample-Efficient and Surrogate-Based Design Optimization of Underwater Vehicle Hullscited by 4
  8. 2025Transfer learning-enhanced deep reinforcement learning for aerodynamic airfoil optimisation subject to structural constraintscited by 4
  9. 2022Deep learning fluid flow reconstruction around arbitrary two-dimensional objects from sparse sensors using conformal mappingscited by 3
  10. 2024Enhancing Vehicle Aerodynamics with Deep Reinforcement Learning in Voxelised Modelscited by 3
  11. 2022Investigation of reinforcement learning for shape optimization of profile extrusion diescited by 2
  12. 2024A reinforcement learning strategy to automate and accelerate h/p-multigrid solverscited by 2
16 more
  1. 2022Non-iterative generation of an optimal mesh for a blade passage using deep reinforcement learningcited by 1
  2. 2023Active Control of Flow over Rotating Cylinder by Multiple Jets using Deep Reinforcement Learningcited by 1
  3. 2023Physics-Driven ML-Based Modelling for Correcting Inverse Estimationcited by 1
  4. 2024Design Optimization of Nuclear Fusion Reactor through Deep Reinforcement Learningcited by 1
  5. 2026Heuristic Learning for Active Flow Control Using Coding Agentscited by 1
  6. 2021Stabilising viscous extensional flows using Reinforcement Learningcited by 0
  7. 2024A mechanism-driven reinforcement learning framework for shape optimization of airfoilscited by 0
  8. 2024Anvil: An integration of artificial intelligence, sampling techniques, and a combined CAD-CFD toolcited by 0
  9. 2024Deep Reinforcement Learning for the Design of Metamaterial Mechanisms with Functional Compliance Controlcited by 0
  10. 2025Reinforcement learning framework for the mechanical design of microelectronic components under multiphysics constraintscited by 0
  11. 2025Reinforcement Learning for Accelerated Aerodynamic Shape Optimisationcited by 0
  12. 2025Oranits: Mission Assignment and Task Offloading in Open RAN-based ITS using Metaheuristic and Deep Reinforcement Learningcited by 0
  13. 2025Transfer learning strategies for accelerating reinforcement-learning-based flow controlcited by 0
  14. 2025DiffeoMorph: Learning to Morph 3D Shapes Using Differentiable Agent-Based Simulationscited by 0
  15. 2026BladeSDF : Unconditional and Conditional Generative Modeling of Representative Blade Geometries Using Signed Distance Functionscited by 0
  16. 2026Large language models for partial differential equation workflowscited by 0