大规模流动控制的强化学习算法即插即用基准测试

摘要

强化学习（RL）在主动流动控制（AFC）领域已展现出显著成效，但由于现有研究采用异构的观测与执行方案、数值模拟设置及评估标准，该领域的进展仍难以客观衡量。当前AFC基准测试虽尝试解决这些问题，但严重依赖外部计算流体动力学（CFD）求解器，缺乏完全可微性，且对三维场景与多智能体系统的支持有限。为突破这些限制，我们推出首个独立、完全可微的AFC强化学习基准套件FluidGym。该套件完全基于PyTorch构建于GPU加速的PICT求解器之上，运行于单一Python框架内，无需外部CFD软件，并提供标准化评估流程。我们通过PPO和SAC算法呈现基线结果，并将所有环境、数据集及训练模型作为公共资源开放。FluidGym实现了控制方法的系统性比较，为基于学习的流动控制研究建立了可扩展基础，项目地址：https://github.com/safe-autonomous-systems/fluidgym。

English

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.

大规模流动控制的强化学习算法即插即用基准测试

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

摘要

Support