Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control

Jannis Becktepe, Aleksandra Franz, Nils Thuerey, Sebastian Peitz
1/21/2026
cs.LG

Official code: safe-autonomous-systems/fluidgym (53 stars, MIT, last commit 2026-04-22).

Abstract

Reinforcement learning (RL) has shown promising results in active flow control (AFC), yet progress in the field remains difficult to assess as existing studies rely on heterogeneous observation and actuation schemes, numerical setups, and evaluation protocols. Current AFC benchmarks attempt to address these issues but heavily rely on external computational fluid dynamics (CFD) solvers, are not fully differentiable, and provide limited 3D and multi-agent support. To overcome these limitations, we introduce FluidGym, the first standalone, fully differentiable benchmark suite for RL in AFC. Built entirely in PyTorch on top of the GPU-accelerated PICT solver, FluidGym runs in a single Python stack, requires no external CFD software, and provides standardized evaluation protocols. We present baseline results with PPO and SAC and release all environments, datasets, and trained models as public resources. FluidGym enables systematic comparison of control methods, establishes a scalable foundation for future research in learning-based flow control, and is available at https://github.com/safe-autonomous-systems/fluidgym.

View on arXivView PDF

Code Implementations(1)

safe-autonomous-systems/fluidgymOfficial100%
MIT

Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control

537C, C++Jan 9, 20266 months agoMIT
benchmark-suitedifferentiable-simulationfluid-dynamicsreinforcement-learning

Similar Papers

HydroGym: A Reinforcement Learning Platform for Fluid Dynamics

88% match2025

Gym-preCICE: Reinforcement Learning Environments for Active Flow Control

87% match1 repo322023

Model-based deep reinforcement learning for accelerated learning from flow simulations

86% match2024

Beacon, a lightweight deep reinforcement learning benchmark library for flow control

85% match1 repo142024

Real-World Fluid Directed Rigid Body Control via Deep Reinforcement Learning

85% match2024

Optimal Parallelization Strategies for Active Flow Control in Deep Reinforcement Learning-Based Computational Fluid Dynamics

84% match2024

Cite this paper

@article{becktepe2026plugandplay,
  title  = {Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control},
  author = {Jannis Becktepe and Aleksandra Franz and Nils Thuerey and Sebastian Peitz},
  year   = {2026},
  eprint = {2601.15015},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2601.15015v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2601.15015.svg)](https://codeofpaper.com/paper/2601.15015)

Discussion