Advanced deep-reinforcement-learning methods for flow control: group-invariant and positional-encoding networks improve learning speed and quality

Documenti analoghi

• Comparison of CNN-based deep learning architectures for unsteady CFD acceleration on small datasets
  di: Khanal, Sangam, et al.
  Pubblicazione: (2025)
• Multi-agent reinforcement learning for the control of three-dimensional Rayleigh-Bénard convection
  di: Vasanth, Joel, et al.
  Pubblicazione: (2024)
• XRePIT: A deep learning-computational fluid dynamics hybrid framework implemented in OpenFOAM for fast, robust, and scalable unsteady simulations
  di: Baral, Shilaj, et al.
  Pubblicazione: (2025)
• Active flow control of a turbulent separation bubble through deep reinforcement learning
  di: Font, Bernat, et al.
  Pubblicazione: (2024)
• Active flow control for drag reduction through multi-agent reinforcement learning on a turbulent cylinder at $Re_D=3900$
  di: Suárez, P., et al.
  Pubblicazione: (2024)