safe-autonomous-systems/ma-ppo-RBC3D-easy-v0

PPO on RBC3D-easy-v0 (FluidGym)

This repository is part of the FluidGym benchmark results. It contains trained Stable Baselines3 agents for the specialized RBC3D-easy-v0 environment.

Evaluation Results

Global Performance (Aggregated across 5 seeds)

Mean Reward: 0.35 ± 0.04

Per-Seed Statistics

Run	Mean Reward	Std Dev
Seed 0	0.33	0.08
Seed 1	0.37	0.06
Seed 2	0.38	0.08
Seed 3	0.28	0.10
Seed 4	0.39	0.05

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")

References

• Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control
• FluidGym GitHub Repository