FluidGym Benchmark Models
Collection
Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control
•
66 items
•
Updated
PPO on RBC2D-medium-v0 (FluidGym)
This repository is part of the FluidGym benchmark results. It contains trained Stable Baselines3 agents for the specialized RBC2D-medium-v0 environment.
Evaluation Results
Global Performance (Aggregated across 5 seeds)
Mean Reward: 0.14 ± 0.07
Per-Seed Statistics
| Run | Mean Reward | Std Dev |
|---|---|---|
| Seed 0 | 0.15 | 1.09 |
| Seed 1 | 0.02 | 1.32 |
| Seed 2 | 0.22 | 1.28 |
| Seed 3 | 0.12 | 1.35 |
| Seed 4 | 0.18 | 1.41 |
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:
from stable_baselines3 import PPO
model = PPO.load("0/ckpt_latest.zip")
- Downloads last month
- -
Collection including safe-autonomous-systems/ppo-RBC2D-medium-v0
Evaluation results
- mean_reward on FluidGym-RBC2D-medium-v0self-reported0.140