This repository is part of the FluidGym benchmark results. It contains trained Stable Baselines3 agents for the specialized Airfoil3D-easy-v0 environment.

Mean Reward: -0.10 ± 0.06

FluidGym is a benchmark for reinforcement learning in active flow control.

Each seed is contained in its own subdirectory. You can load a model using:

Important: The models were trained using fluidgym==0.0.2. In order to use them with newer versions of FluidGym, you need to wrap the environment with a FlattenObservation wrapper as shown below: