safe-autonomous-systems/ma-ppo-RBC2D-medium-v0

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: 0.06 ± 0.15

Per-Seed Statistics

Run	Mean Reward	Std Dev
Seed 0	-0.06	1.56
Seed 1	0.27	1.35
Seed 2	0.21	0.93
Seed 3	-0.12	1.43
Seed 4	0.00	1.38

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")

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:

import fluidgym
from fluidgym.wrappers import FlattenObservation
from stable_baselines3 import PPO

env = fluidgym.make("RBC2D-medium-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
• FluidGym GitHub Repository