|
|
--- |
|
|
library_name: stable-baselines3 |
|
|
tags: |
|
|
- reinforcement-learning |
|
|
- stable-baselines3 |
|
|
- deep-reinforcement-learning |
|
|
- fluidgym |
|
|
- active-flow-control |
|
|
- fluid-dynamics |
|
|
- simulation |
|
|
- RBC2D-hard-v0 |
|
|
model-index: |
|
|
- name: PPO-RBC2D-hard-v0 |
|
|
results: |
|
|
- task: |
|
|
type: reinforcement-learning |
|
|
name: reinforcement-learning |
|
|
dataset: |
|
|
name: FluidGym-RBC2D-hard-v0 |
|
|
type: fluidgym |
|
|
metrics: |
|
|
- type: mean_reward |
|
|
value: -0.31 |
|
|
name: mean_reward |
|
|
|
|
|
|
|
|
--- |
|
|
|
|
|
# PPO on RBC2D-hard-v0 (FluidGym) |
|
|
|
|
|
This repository is part of the **FluidGym** benchmark results. It contains trained Stable Baselines3 agents for the specialized **RBC2D-hard-v0** environment. |
|
|
|
|
|
## Evaluation Results |
|
|
|
|
|
### Global Performance (Aggregated across 5 seeds) |
|
|
**Mean Reward:** -0.31 ± 0.03 |
|
|
|
|
|
### Per-Seed Statistics |
|
|
| Run | Mean Reward | Std Dev | |
|
|
| --- | --- | --- | |
|
|
| Seed 0 | -0.32 | 2.24 | |
|
|
| Seed 1 | -0.27 | 2.19 | |
|
|
| Seed 2 | -0.36 | 2.50 | |
|
|
| Seed 3 | -0.29 | 2.22 | |
|
|
| Seed 4 | -0.30 | 2.35 | |
|
|
|
|
|
## About FluidGym |
|
|
FluidGym is a benchmark for reinforcement learning in active flow control. |
|
|
|
|
|
## Usage |
|
|
Each seed is contained in its own subdirectory. You can load a model using: |
|
|
```python |
|
|
from stable_baselines3 import PPO |
|
|
model = PPO.load("0/ckpt_latest.zip") |
|
|
|
|
|
**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: |
|
|
```python |
|
|
import fluidgym |
|
|
from fluidgym.wrappers import FlattenObservation |
|
|
from stable_baselines3 import PPO |
|
|
|
|
|
env = fluidgym.make("RBC2D-hard-v0") |
|
|
env = FlattenObservation(env) |
|
|
model = PPO.load("path_to_model/ckpt_latest.zip") |
|
|
|
|
|
obs, info = env.reset(seed=42) |
|
|
|
|
|
action, _ = model.predict(obs, deterministic=True) |
|
|
obs, reward, terminated, truncated, info = env.step(action) |
|
|
``` |
|
|
|
|
|
## References |
|
|
|
|
|
* [Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control](http://arxiv.org/abs/2601.15015) |
|
|
* [FluidGym GitHub Repository](https://github.com/safe-autonomous-systems/fluidgym) |
|
|
|
