mlsanityData to 7 Oct 2026

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

arXiv 2601.15015 ↗First posted 21 Jan 2026cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

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, SAC, DPC, and TD-MPC, 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 github.com/safe-autonomous-systems/fluidgym.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 29 of its 89 references that are in the map. First posted on arXiv 21 Jan 2026.

Builds on

29 of 89 references.

References · 29

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 781
  4. 2017Deep Reinforcement Learning that Matterscited by 727
  5. 2022Temporal Difference Learning for Model Predictive Controlcited by 375
  6. 2020PettingZoo: Gym for Multi-Agent Reinforcement Learningcited by 209
  7. 2022Accelerated Policy Learning with Parallel Differentiable Simulationcited by 92
  8. 2024Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equationscited by 87
  9. 2019A review on Deep Reinforcement Learning for Fluid Mechanicscited by 65
  10. 2023TorchRL: A data-driven decision-making library for PyTorchcited by 59
  11. 2021Scientific multi-agent reinforcement learning for wall-models of turbulent flowscited by 52
  12. 2023Effective control of two-dimensional Rayleigh--B'enard convection: invariant multi-agent reinforcement learning is all you needcited by 25
17 more
  1. 2024SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learningcited by 24
  2. 2020Learning to Represent Action Values as a Hypergraph on the Action Verticescited by 22
  3. 2020Deep Learning Alternative to Explicit Model Predictive Control for Unknown Nonlinear Systemscited by 21
  4. 2022Solving Continuous Control via Q-learningcited by 21
  5. 2023Distributed Control of Partial Differential Equations Using Convolutional Reinforcement Learningcited by 21
  6. 2024Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulationcited by 14
  7. 2024PDE Control Gym: A Benchmark for Data-Driven Boundary Control of Partial Differential Equationscited by 8
  8. 2019FLEXI: A high order discontinuous Galerkin framework for hyperbolic-parabolic conservation lawscited by 7
  9. 2025Deep Reinforcement Learning for Active Flow Control around a Three-Dimensional Flow-Separated Wing at Re = 1,000cited by 6
  10. 2025PICT -- A Differentiable, GPU-Accelerated Multi-Block PISO Solver for Simulation-Coupled Learning Tasks in Fluid Dynamicscited by 5
  11. 2023Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning Algorithmscited by 4
  12. 2024Beacon, a lightweight deep reinforcement learning benchmark library for flow controlcited by 3
  13. 2023Gym-preCICE: Reinforcement Learning Environments for Active Flow Controlcited by 2
  14. 2025Control of Rayleigh-B'enard Convection: Effectiveness of Reinforcement Learning in the Turbulent Regimecited by 2
  15. 2025Physics-informed Neural-operator Predictive Control for Drag Reduction in Turbulent Flowscited by 2
  16. 2022An Optical Control Environment for Benchmarking Reinforcement Learning Algorithmscited by 1
  17. 2025Gym-TORAX: Open-source software for integrating reinforcement learning with plasma control simulators in tokamak researchcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Heuristic Learning for Active Flow Control Using Coding Agentscited by 1
  2. 2026Koopman-based surrogate modeling for reinforcement-learning-control of Rayleigh-Benard convectioncited by 0