Model-based deep reinforcement learning for accelerated learning from flow simulations

1 code implementation • 26 Feb 2024 • Andre Weiner, Janis Geise

Employing simulation-based environments in reinforcement learning enables a priori end-to-end optimization of the control system, provides a virtual testbed for safety-critical control applications, and allows to gain a deep understanding of the control mechanisms.

Model-based Reinforcement Learning reinforcement-learning

Combining Machine Learning with Computational Fluid Dynamics using OpenFOAM and SmartSim

1 code implementation • 25 Feb 2024 • Tomislav Maric, Mohammed Elwardi Fadeli, Alessandro Rigazzi, Andrew Shao, Andre Weiner

Combining machine learning (ML) with computational fluid dynamics (CFD) opens many possibilities for improving simulations of technical and natural systems.