{"id":35147,"date":"2026-04-13T14:10:46","date_gmt":"2026-04-13T14:10:46","guid":{"rendered":"https:\/\/lamarr-institute.org\/publication\/plug-and-play-benchmarking-of-reinforcement-learning-algorithms-for-large-scale-flow-control\/"},"modified":"2026-06-08T13:17:57","modified_gmt":"2026-06-08T13:17:57","slug":"plug-and-play-benchmarking-of-reinforcement-learning-algorithms-for-large-scale-flow-control","status":"publish","type":"publication","link":"https:\/\/lamarr-institute.org\/de\/publication\/plug-and-play-benchmarking-of-reinforcement-learning-algorithms-for-large-scale-flow-control\/","title":{"rendered":"Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control"},"content":{"rendered":"<p>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.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>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 [&hellip;]<\/p>\n","protected":false},"author":12,"featured_media":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"publication-type":[30],"class_list":["post-35147","publication","type-publication","status-publish","hentry","publication-type-article"],"acf":[],"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/35147","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/types\/publication"}],"author":[{"embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/users\/12"}],"version-history":[{"count":0,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/35147\/revisions"}],"wp:attachment":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/media?parent=35147"}],"wp:term":[{"taxonomy":"publication-type","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-type?post=35147"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}