metadata
library_name: stable-baselines3
tags:
- reinforcement-learning
- stable-baselines3
- deep-reinforcement-learning
- fluidgym
- active-flow-control
- fluid-dynamics
- simulation
- RBC2D-medium-v0
model-index:
- name: SAC-RBC2D-medium-v0
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FluidGym-RBC2D-medium-v0
type: fluidgym
metrics:
- type: mean_reward
value: 0.78
name: mean_reward
predict_config:
preview_file: replay.mp4
SAC 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: 0.78 ± 0.05
Per-Seed Statistics
| Run | Mean Reward | Std Dev |
|---|---|---|
| Seed 0 | 0.72 | 0.72 |
| Seed 1 | 0.75 | 0.62 |
| Seed 2 | 0.80 | 0.78 |
| Seed 3 | 0.77 | 0.59 |
| Seed 4 | 0.88 | 0.72 |
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 SAC
model = SAC.load("0/ckpt_latest.zip")