{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T22:08:13Z","timestamp":1790114893268,"version":"4.0.1"},"reference-count":85,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,30]],"date-time":"2026-08-30T00:00:00Z","timestamp":1788048000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["101040379"],"award-info":[{"award-number":["101040379"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Machine Learning with Applications"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.mlwa.2026.100996","type":"journal-article","created":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T06:44:29Z","timestamp":1788590669000},"page":"100996","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Eigenspace-based reinforcement learning acceleration of statistical convergence in turbulent flows"],"prefix":"10.1016","volume":"25","author":[{"given":"N\u00faria","family":"Masclans","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2437-259X","authenticated-orcid":false,"given":"Llu\u00eds","family":"Jofre","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.mlwa.2026.100996_b1","first-page":"425","article-title":"OpenACC acceleration of parallel direct numerical simulation of turbulent flows","volume":"11","author":"Abdellatif","year":"2025","journal-title":"Journal of Applied and Computational Mechanics"},{"key":"10.1016\/j.mlwa.2026.100996_b2","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","article-title":"Deep reinforcement learning: A brief survey","volume":"34","author":"Arulkumaran","year":"2017","journal-title":"IEEE Signal Processing Magazine"},{"key":"10.1016\/j.mlwa.2026.100996_b3","doi-asserted-by":"crossref","DOI":"10.1080\/14685240701506896","article-title":"Presentation of anisotropy properties of turbulence, invariants versus eigenvalue approaches","volume":"8","author":"Banerjee","year":"2007","journal-title":"Journal of Turbulence"},{"key":"10.1016\/j.mlwa.2026.100996_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128166","article-title":"A survey on physics informed reinforcement learning: Review and open problems","volume":"287","author":"Banerjee","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.mlwa.2026.100996_b5","doi-asserted-by":"crossref","first-page":"15344","DOI":"10.1073\/pnas.1814058116","article-title":"Learning data-driven discretizations for partial differential equations","volume":"116","author":"Bar-Sinai","year":"2019","journal-title":"Proceedings of the National Academy of Sciences of the United States of America"},{"key":"10.1016\/j.mlwa.2026.100996_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.jcp.2019.108910","article-title":"Deep neural networks for data-driven les closure models","volume":"398","author":"Beck","year":"2019","journal-title":"Journal of Computational Physics"},{"key":"10.1016\/j.mlwa.2026.100996_b7","doi-asserted-by":"crossref","DOI":"10.1017\/jfm.2013.674","article-title":"Velocity statistics in turbulent channel flow up to Re\u03c4,=4000","volume":"742","author":"Bernardini","year":"2014","journal-title":"Journal of Fluid Mechanics"},{"key":"10.1016\/j.mlwa.2026.100996_b8","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1146\/annurev-fluid-010719-060214","article-title":"Machine learning for fluid mechanics","volume":"52","author":"Brunton","year":"2020","journal-title":"Annual Review of Fluid Mechanics"},{"key":"10.1016\/j.mlwa.2026.100996_b9","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1017\/S0022112005008578","article-title":"State estimation in wall-bounded flow systems. Part 2. Turbulent flows","volume":"552","author":"Chevalier","year":"2006","journal-title":"Journal of Fluid Mechanics"},{"key":"10.1016\/j.mlwa.2026.100996_b10","doi-asserted-by":"crossref","DOI":"10.1063\/5.0035627","article-title":"Accelerating explicit method for Poisson\u2019s equation using machine learning techniques","volume":"2312","author":"Chikitkin","year":"2020","journal-title":"AIP Conference Proceedings"},{"key":"10.1016\/j.mlwa.2026.100996_b11","doi-asserted-by":"crossref","DOI":"10.1115\/1.4042820","article-title":"Discrete energy-conservation properties in the numerical simulation of the Navier-Stokes equations","volume":"71","author":"Coppola","year":"2019","journal-title":"Applied Mechanics Reviews"},{"key":"10.1016\/j.mlwa.2026.100996_b12","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.jcp.2019.01.007","article-title":"Numerically stable formulations of convective terms for turbulent compressible flows","volume":"382","author":"Coppola","year":"2019","journal-title":"Journal of Computational Physics"},{"key":"10.1016\/j.mlwa.2026.100996_b13","first-page":"0822","article-title":"Modeling of structural uncertainties in Reynolds-averaged Navier-Stokes closures","volume":"25","author":"Emory","year":"2013","journal-title":"Physics of Fluids"},{"key":"10.1016\/j.mlwa.2026.100996_b14","first-page":"1","article-title":"Modeling structural uncertainties in Reynolds-averaged computations of shock\/boundary layer interactions","volume":"479","author":"Emory","year":"2011","journal-title":"AIAA Paper"},{"key":"10.1016\/j.mlwa.2026.100996_b15","series-title":"Computational methods for fluid dynamics, vol. 3","author":"Ferziger","year":"2002"},{"key":"10.1016\/j.mlwa.2026.100996_b16","article-title":"Active flow control of a turbulent separation bubble through deep reinforcement learning","volume":"2753","author":"Font","year":"2024","journal-title":"Journal of Physics: Conference Series"},{"key":"10.1016\/j.mlwa.2026.100996_b17","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1017\/jfm.2019.238","article-title":"Super-resolution reconstruction of turbulent flows with machine learning","volume":"870","author":"Fukami","year":"2019","journal-title":"Journal of Fluid Mechanics"},{"key":"10.1016\/j.mlwa.2026.100996_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.compfluid.2021.104973","article-title":"A review on deep reinforcement learning for fluid mechanics","volume":"225","author":"Garnier","year":"2021","journal-title":"Computers & Fluids"},{"key":"10.1016\/j.mlwa.2026.100996_b19","series-title":"Classical mechanics","author":"Goldstein","year":"1980"},{"key":"10.1016\/j.mlwa.2026.100996_b20","doi-asserted-by":"crossref","DOI":"10.1063\/1.4807067","article-title":"A framework for epistemic uncertainty quantification of turbulent scalar flux models for Reynolds-averaged Navier-Stokes simulations","volume":"25","author":"Gorl\u00e9","year":"2013","journal-title":"Physics of Fluids"},{"key":"10.1016\/j.mlwa.2026.100996_b21","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1137\/S003614450036757X","article-title":"Strong stability-preserving high-order time discretization methods","volume":"43","author":"Gottlieb","year":"2001","journal-title":"SIAM Review"},{"key":"10.1016\/j.mlwa.2026.100996_b22","series-title":"TF-Agents: A library for reinforcement learning in TensorFlow (version 0.18.0) [computer software]","author":"Guadarrama","year":"2018"},{"key":"10.1016\/j.mlwa.2026.100996_b23","series-title":"Proceedings of the 35th international conference on machine learning","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"10.1016\/j.mlwa.2026.100996_b24","series-title":"Deep recurrent Q-learning for partially observable MDPs","author":"Hausknecht","year":"2017"},{"key":"10.1016\/j.mlwa.2026.100996_b25","doi-asserted-by":"crossref","DOI":"10.1063\/1.2162185","article-title":"Scaling of the velocity fluctuations in turbulent channels up to re\u03c4,=2003","volume":"18","author":"Hoyas","year":"2006","journal-title":"Physics of Fluids"},{"key":"10.1016\/j.mlwa.2026.100996_b26","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1017\/S0022112091002033","article-title":"The minimal flow unit in near-wall turbulence","volume":"225","author":"Jim\u00e9nez","year":"1991","journal-title":"Journal of Fluid Mechanics"},{"key":"10.1016\/j.mlwa.2026.100996_b27","doi-asserted-by":"crossref","first-page":"4637","DOI":"10.21105\/joss.04637","article-title":"RHEA - an open-source reproducible hybrid-architecture flow solver Engineered for Academia","volume":"8","author":"Jofre","year":"2023","journal-title":"Journal of Open Source Software"},{"key":"10.1016\/j.mlwa.2026.100996_b28","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1007\/s10494-017-9844-8","article-title":"A framework for characterizing structural uncertainty in large-eddy simulation closures","volume":"100","author":"Jofre","year":"2018","journal-title":"Flow Turbul. Combust."},{"key":"10.1016\/j.mlwa.2026.100996_b29","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1016\/j.ijheatfluidflow.2019.04.014","article-title":"Eigensensitivity analysis of subgrid-scale stresses in large-eddy simulation of a turbulent axisymmetric jet","volume":"77","author":"Jofre","year":"2019","journal-title":"International Journal of Heat and Fluid Flow"},{"key":"10.1016\/j.mlwa.2026.100996_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijmultiphaseflow.2019.103198","article-title":"Data-driven dimensional analysis of heat transfer in irradiated particle-laden turbulent flow","volume":"125","author":"Jofre","year":"2020","journal-title":"The International Journal of Multiphase Flow"},{"key":"10.1016\/j.mlwa.2026.100996_b31","unstructured":"Kakade, S., & Langford, J. (2002). Approximately optimal approximate reinforcement learning. In Proceedings of the 19th international conference on machine learning (pp. 267\u2013274)."},{"key":"10.1016\/j.mlwa.2026.100996_b32","unstructured":"Kindlmann, G. (2004). Superquadric tensor glyphs. In Proc. 6th joint eurographics-IEEE TCVG conference (pp. 147\u2013154)."},{"key":"10.1016\/j.mlwa.2026.100996_b33","series-title":"Teem: Tools to process and visualize scientific data and images [computer software]","author":"Kindlmann","year":"2003"},{"key":"10.1016\/j.mlwa.2026.100996_b34","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.1137\/S0363012901385691","article-title":"On actor-critic algorithms","volume":"42","author":"Konda","year":"2003","journal-title":"SIAM Journal on Control and Optimization"},{"key":"10.1016\/j.mlwa.2026.100996_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.compfluid.2025.106854","article-title":"Invariant control strategies for active flow control using graph neural networks","volume":"303","author":"Kurz","year":"2025","journal-title":"Computers & Fluids"},{"key":"10.1016\/j.mlwa.2026.100996_b36","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1017\/jfm.2015.268","article-title":"Direct numerical simulation of turbulent channel flow up to Re\u03c4\u22485200","volume":"774","author":"Lee","year":"2015","journal-title":"Journal of Fluid Mechanics"},{"key":"10.1016\/j.mlwa.2026.100996_b37","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1017\/jfm.2014.575","article-title":"Time-resolved evolution of coherent structures in turbulent channels: characterization of eddies and cascades","volume":"759","author":"Lozano-Dur\u00e1n","year":"2014","journal-title":"Journal of Fluid Mechanics"},{"key":"10.1016\/j.mlwa.2026.100996_b38","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-018-07210-0","article-title":"Deep learning for universal linear embeddings of nonlinear dynamics","volume":"9","author":"Lusch","year":"2018","journal-title":"Nature Communications"},{"key":"10.1016\/j.mlwa.2026.100996_b39","series-title":"REP-DRL for 3D turbulent channel flow [computer software]","author":"Masclans","year":"2026"},{"key":"10.1016\/j.mlwa.2026.100996_b40","series-title":"9th European congress on computational methods in applied sciences and engineering","first-page":"1","article-title":"Data-driven acceleration of statistical convergence in turbulent flows","author":"Masclans","year":"2024"},{"key":"10.1016\/j.mlwa.2026.100996_b41","unstructured":"Mnih, V., Badia, A., Mirza, M., Graves, A., Lillicrap, T., Harley, T., Silver, D., & Kavukcuoglu, K. (2016). Asynchronous Methods for Deep Reinforcement Learning. In Proceedings of the 33rd international conference on machine learning (pp. 1928\u20131937)."},{"key":"10.1016\/j.mlwa.2026.100996_b42","series-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"10.1016\/j.mlwa.2026.100996_b43","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"10.1016\/j.mlwa.2026.100996_b44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000086","article-title":"Model-based reinforcement learning: A survey","volume":"16","author":"Moerland","year":"2023","journal-title":"Foundations and Trends in Machine Learning"},{"key":"10.1016\/j.mlwa.2026.100996_b45","series-title":"Towards active flow control strategies through deep reinforcement learning","author":"Montal\u00e0","year":"2024"},{"key":"10.1016\/j.mlwa.2026.100996_b46","doi-asserted-by":"crossref","DOI":"10.1016\/j.cpc.2026.110233","article-title":"RHEA-X: Distributed GPU-resident high-fidelity flow solver for multiphysics turbulence","volume":"326","author":"Monteiro","year":"2026","journal-title":"Computer Physics Communications"},{"key":"10.1016\/j.mlwa.2026.100996_b47","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1063\/1.869966","article-title":"Direct numerical simulation of turbulent channel flow up to re\u03c4,=590","volume":"11","author":"Moser","year":"1999","journal-title":"Physics of Fluids"},{"key":"10.1016\/j.mlwa.2026.100996_b48","doi-asserted-by":"crossref","DOI":"10.1063\/1.4993489","article-title":"Reducing spin-up time for simulations of turbulent channel flow","volume":"29","author":"Nelson","year":"2017","journal-title":"Physics of Fluids"},{"key":"10.1016\/j.mlwa.2026.100996_b49","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevFluids.4.093902","article-title":"Controlled gliding and perching through deep-reinforcement-learning","volume":"4","author":"Novati","year":"2019","journal-title":"Physical Review Fluids"},{"key":"10.1016\/j.mlwa.2026.100996_b50","doi-asserted-by":"crossref","DOI":"10.1088\/1748-3190\/aa6311","article-title":"Synchronisation through learning for two self-propelled swimmers","volume":"12","author":"Novati","year":"2017","journal-title":"Bioinspiration and Biomimetics"},{"key":"10.1016\/j.mlwa.2026.100996_b51","doi-asserted-by":"crossref","unstructured":"Obiols-Sales, O., Vishnu, A., Malaya, N., & Chandramowlishwaran, A. (2020). CFDNet: a deep learning-based accelerator for fluid simulations. In Proceedings of the 34th ACM international conference on supercomputing.","DOI":"10.1145\/3392717.3392772"},{"key":"10.1016\/j.mlwa.2026.100996_b52","doi-asserted-by":"crossref","DOI":"10.1063\/1.4866813","article-title":"Estimating uncertainties in statistics computed from direct numerical simulation","volume":"26","author":"Oliver","year":"2014","journal-title":"Physics of Fluids"},{"key":"10.1016\/j.mlwa.2026.100996_b53","doi-asserted-by":"crossref","DOI":"10.1016\/j.jocs.2022.101707","article-title":"Using machine learning at scale in numerical simulations with SmartSim: An application to ocean climate modeling","volume":"62","author":"Partee","year":"2022","journal-title":"The Journal of Computational Science"},{"key":"10.1016\/j.mlwa.2026.100996_b54","series-title":"Turbulent flows","author":"Pope","year":"2000"},{"key":"10.1016\/j.mlwa.2026.100996_b55","series-title":"Markov decision processes: discrete stochastic dynamic programming","author":"Puterman","year":"2014"},{"key":"10.1016\/j.mlwa.2026.100996_b56","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1017\/jfm.2019.62","article-title":"Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control","volume":"865","author":"Rabault","year":"2019","journal-title":"Journal of Fluid Mechanics"},{"key":"10.1016\/j.mlwa.2026.100996_b57","doi-asserted-by":"crossref","DOI":"10.1063\/1.5116415","article-title":"Accelerating deep reinforcement learning strategies of flow control through a multi-environment approach","volume":"31","author":"Rabault","year":"2019","journal-title":"Physics of Fluids"},{"key":"10.1016\/j.mlwa.2026.100996_b58","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1613\/jair.3987","article-title":"A survey of multi-objective sequential decision-making","volume":"48","author":"Roijers","year":"2013","journal-title":"Journal of Artificial Intelligence Research"},{"key":"10.1016\/j.mlwa.2026.100996_b59","series-title":"Principles of mathematical analysis","author":"Rudin","year":"1976"},{"key":"10.1016\/j.mlwa.2026.100996_b60","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1016\/j.jcp.2017.07.005","article-title":"A fast algorithm for the estimation of statistical error in DNS (or experimental) time averages","volume":"347","author":"Russo","year":"2017","journal-title":"Journal of Computational Physics"},{"key":"10.1016\/j.mlwa.2026.100996_b61","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., & Moritz, P. (2015). Trust region policy optimization. In Proceedings of the 32nd international conference on machine learning (pp. 1889\u20131897)."},{"key":"10.1016\/j.mlwa.2026.100996_b62","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"10.1016\/j.mlwa.2026.100996_b63","series-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"10.1016\/j.mlwa.2026.100996_b64","doi-asserted-by":"crossref","DOI":"10.1063\/1.4791606","article-title":"Reynolds-number scaling of turbulent channel flow","volume":"25","author":"Schultz","year":"2013","journal-title":"Physics of Fluids"},{"key":"10.1016\/j.mlwa.2026.100996_b65","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1063\/1.861942","article-title":"Realizability of Reynolds-stress turbulence models","volume":"20","author":"Schumann","year":"1977","journal-title":"Physics of Fluids"},{"key":"10.1016\/j.mlwa.2026.100996_b66","doi-asserted-by":"crossref","DOI":"10.1016\/j.compfluid.2023.106046","article-title":"On the convergence of statistics in simulations of stationary incompressible turbulent flows","volume":"266","author":"Shirian","year":"2023","journal-title":"Computers & Fluids"},{"key":"10.1016\/j.mlwa.2026.100996_b67","doi-asserted-by":"crossref","DOI":"10.1016\/j.jcp.2020.109811","article-title":"Dpm: A deep learning pde augmentation method with application to large-eddy simulation","volume":"423","author":"Sirignano","year":"2020","journal-title":"Journal of Computational Physics"},{"key":"10.1016\/j.mlwa.2026.100996_b68","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1146\/annurev-fluid-122109-160753","article-title":"High\u2013Reynolds number wall turbulence","volume":"43","author":"Smits","year":"2011","journal-title":"Annual Review of Fluid Mechanics"},{"key":"10.1016\/j.mlwa.2026.100996_b69","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1007\/BF01575099","article-title":"On the realizability of Reynolds stress turbulence closures","volume":"9","author":"Speziale","year":"1993","journal-title":"Journal of Scientific Computing"},{"key":"10.1016\/j.mlwa.2026.100996_b70","series-title":"Active flow control for drag reduction through multi-agent reinforcement learning on a turbulent cylinder at red=3900","author":"Su\u00e1rez","year":"2024"},{"key":"10.1016\/j.mlwa.2026.100996_b71","series-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"10.1016\/j.mlwa.2026.100996_b72","series-title":"Advances in neural information processing systems","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"Sutton","year":"1999"},{"key":"10.1016\/j.mlwa.2026.100996_b73","doi-asserted-by":"crossref","DOI":"10.1063\/5.0006492","article-title":"Robust active flow control over a range of Reynolds numbers using an artificial neural network trained through deep reinforcement learning","volume":"32","author":"Tang","year":"2020","journal-title":"Physics of Fluids"},{"key":"10.1016\/j.mlwa.2026.100996_b74","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevFluids.4.044603","article-title":"Eigenvector perturbation methodology for uncertainty quantification of turbulence models","volume":"4","author":"Thompson","year":"2019","journal-title":"Physical Review Fluids"},{"key":"10.1016\/j.mlwa.2026.100996_b75","doi-asserted-by":"crossref","unstructured":"Tsukahara, T., Seki, Y., Kawamura, H., & Tochio, D. (2005). DNS of turbulent channel flow at very low Reynolds numbers. In Proceeding of fourth international symposium on turbulence and shear flow phenomena.","DOI":"10.1615\/TSFP4.1550"},{"key":"10.1016\/j.mlwa.2026.100996_b76","doi-asserted-by":"crossref","DOI":"10.3390\/act11120359","article-title":"Deep reinforcement learning for flow control exploits different physics for increasing Reynolds number regimes","volume":"11","author":"Varela","year":"2022","journal-title":"Actuators"},{"key":"10.1016\/j.mlwa.2026.100996_b77","doi-asserted-by":"crossref","first-page":"5849","DOI":"10.1073\/pnas.1800923115","article-title":"Efficient collective swimming by harnessing vortices through deep reinforcement learning","volume":"115","author":"Verma","year":"2018","journal-title":"Proceedings of the National Academy of Sciences of the United States of America"},{"key":"10.1016\/j.mlwa.2026.100996_b78","doi-asserted-by":"crossref","DOI":"10.1063\/5.0153181","article-title":"Effective control of two-dimensional Rayleigh\u2013B\u00e9nard convection: Invariant multi-agent reinforcement learning is all you need","volume":"35","author":"Vignon","year":"2023","journal-title":"Physics of Fluids"},{"key":"10.1016\/j.mlwa.2026.100996_b79","doi-asserted-by":"crossref","DOI":"10.1063\/1.4861064","article-title":"Comparison of direct numerical simulation databases of turbulent channel flow at Re\u03c4=180","volume":"26","author":"Vreman","year":"2014","journal-title":"Physics of Fluids"},{"key":"10.1016\/j.mlwa.2026.100996_b80","doi-asserted-by":"crossref","DOI":"10.1063\/1.4819390","article-title":"Towards scalable parallel-in-time turbulent flow simulations","volume":"25","author":"Wang","year":"2013","journal-title":"Physics of Fluids"},{"key":"10.1016\/j.mlwa.2026.100996_b81","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1023\/A:1022672621406","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"Williams","year":"1992","journal-title":"Machine Learning"},{"key":"10.1016\/j.mlwa.2026.100996_b82","doi-asserted-by":"crossref","first-page":"941","DOI":"10.1016\/j.cma.2016.10.025","article-title":"A random matrix approach for quantifying model-form uncertainties in turbulence modeling","volume":"313","author":"Xiao","year":"2017","journal-title":"Computer Methods in Applied Mechanics and Engineering"},{"key":"10.1016\/j.mlwa.2026.100996_b83","first-page":"14610","article-title":"A generalized algorithm for multi-objective reinforcement learning and policy adaptation","volume":"vol. 32","author":"Yang","year":"2019"},{"key":"10.1016\/j.mlwa.2026.100996_b84","series-title":"Computational fluid dynamics: its carbon footprint and role in carbon emission reduction","author":"Yang","year":"2024"},{"key":"10.1016\/j.mlwa.2026.100996_b85","doi-asserted-by":"crossref","DOI":"10.1017\/jfm.2025.27","article-title":"Reinforcement-learning-based control of turbulent channel flows at high Reynolds numbers","volume":"1006","author":"Zhou","year":"2025","journal-title":"Journal of Fluid Mechanics"}],"container-title":["Machine Learning with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666827026001611?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666827026001611?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T21:41:40Z","timestamp":1790113300000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2666827026001611"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":85,"alternative-id":["S2666827026001611"],"URL":"https:\/\/doi.org\/10.1016\/j.mlwa.2026.100996","relation":{},"ISSN":["2666-8270"],"issn-type":[{"value":"2666-8270","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Eigenspace-based reinforcement learning acceleration of statistical convergence in turbulent flows","name":"articletitle","label":"Article Title"},{"value":"Machine Learning with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.mlwa.2026.100996","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"100996"}}