{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T15:42:33Z","timestamp":1778773353057,"version":"3.51.4"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"8000","license":[{"start":{"date-parts":[[2024,2,21]],"date-time":"2024-02-21T00:00:00Z","timestamp":1708473600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,2,21]],"date-time":"2024-02-21T00:00:00Z","timestamp":1708473600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nature"],"published-print":{"date-parts":[[2024,2,22]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    For stable and efficient fusion energy production using a tokamak reactor, it is essential to maintain a high-pressure hydrogenic plasma without plasma disruption. Therefore, it is necessary to actively control the tokamak based on the observed plasma state, to manoeuvre high-pressure plasma while avoiding tearing instability, the leading cause of disruptions. This presents an obstacle-avoidance problem for which artificial intelligence based on reinforcement learning has recently shown remarkable performance\n                    <jats:sup>1\u20134<\/jats:sup>\n                    . However, the obstacle here, the tearing instability, is difficult to forecast and is highly prone to terminating plasma operations, especially in the ITER baseline scenario. Previously, we developed a multimodal dynamic model that estimates the likelihood of future tearing instability based on signals from multiple diagnostics and actuators\n                    <jats:sup>5<\/jats:sup>\n                    . Here we harness this dynamic model as a training environment for reinforcement-learning artificial intelligence, facilitating automated instability prevention. We demonstrate artificial intelligence control to lower the possibility of disruptive tearing instabilities in DIII-D\n                    <jats:sup>6<\/jats:sup>\n                    , the largest magnetic fusion facility in the United States. The controller maintained the tearing likelihood under a given threshold, even\u00a0under relatively unfavourable conditions of low safety factor and low torque. In particular, it allowed the plasma to actively track the stable path within the time-varying operational space while maintaining H-mode performance, which was challenging with traditional preprogrammed control. This controller paves the path to developing stable high-performance operational scenarios for future use in ITER.\n                  <\/jats:p>","DOI":"10.1038\/s41586-024-07024-9","type":"journal-article","created":{"date-parts":[[2024,2,21]],"date-time":"2024-02-21T12:02:21Z","timestamp":1708516941000},"page":"746-751","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":125,"title":["Avoiding fusion plasma tearing instability with deep reinforcement learning"],"prefix":"10.1038","volume":"626","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0635-0282","authenticated-orcid":false,"given":"Jaemin","family":"Seo","sequence":"first","affiliation":[]},{"given":"SangKyeun","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Azarakhsh","family":"Jalalvand","sequence":"additional","affiliation":[]},{"given":"Rory","family":"Conlin","sequence":"additional","affiliation":[]},{"given":"Andrew","family":"Rothstein","sequence":"additional","affiliation":[]},{"given":"Joseph","family":"Abbate","sequence":"additional","affiliation":[]},{"given":"Keith","family":"Erickson","sequence":"additional","affiliation":[]},{"given":"Josiah","family":"Wai","sequence":"additional","affiliation":[]},{"given":"Ricardo","family":"Shousha","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4212-3247","authenticated-orcid":false,"given":"Egemen","family":"Kolemen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,2,21]]},"reference":[{"key":"7024_CR1","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V. et al. Human-level control through deep reinforcement learning. Nature 518, 529\u2013533 (2015).","journal-title":"Nature"},{"key":"7024_CR2","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/j.neucom.2017.06.066","volume":"272","author":"Y Cheng","year":"2018","unstructured":"Cheng, Y. & Zhang, W. Concise deep reinforcement learning obstacle avoidance for underactuated unmanned marine vessels. Neurocomputing 272, 63\u201373 (2018).","journal-title":"Neurocomputing"},{"key":"7024_CR3","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1038\/s41586-021-04301-9","volume":"602","author":"J Degrave","year":"2022","unstructured":"Degrave, J. et al. Magnetic control of tokamak plasmas through deep reinforcement learning. Nature 602, 414\u2013419 (2022).","journal-title":"Nature"},{"key":"7024_CR4","doi-asserted-by":"publisher","first-page":"086049","DOI":"10.1088\/1741-4326\/ac79be","volume":"62","author":"J Seo","year":"2022","unstructured":"Seo, J. et al. Development of an operation trajectory design algorithm for control of multiple 0D parameters using deep reinforcement learning in KSTAR. Nucl. Fusion 62, 086049 (2022).","journal-title":"Nucl. Fusion"},{"key":"7024_CR5","doi-asserted-by":"crossref","unstructured":"Seo, J. et al. Multimodal prediction of tearing instabilities in a tokamak. In 2023 International Joint Conference on Neural Networks (IJCNN) 1\u20138 (IEEE, 2023).","DOI":"10.1109\/IJCNN54540.2023.10191359"},{"key":"7024_CR6","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1088\/0029-5515\/42\/5\/313","volume":"42","author":"J Luxon","year":"2002","unstructured":"Luxon, J. A design retrospective of the DIII-D tokamak. Nucl. Fusion 42, 614 (2002).","journal-title":"Nucl. Fusion"},{"key":"7024_CR7","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1038\/s42254-022-00547-y","volume":"5","author":"R Betti","year":"2023","unstructured":"Betti, R. A milestone in fusion research is reached. Nat. Rev. Phys. 5, 6\u20138 (2023).","journal-title":"Nat. Rev. Phys."},{"key":"7024_CR8","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1038\/s41586-022-05008-1","volume":"609","author":"H Han","year":"2022","unstructured":"Han, H. et al. A sustained high-temperature fusion plasma regime facilitated by fast ions. Nature 609, 269\u2013275 (2022).","journal-title":"Nature"},{"key":"7024_CR9","doi-asserted-by":"publisher","first-page":"eabq5273","DOI":"10.1126\/sciadv.abq5273","volume":"9","author":"Y Song","year":"2023","unstructured":"Song, Y. et al. Realization of thousand-second improved confinement plasma with Super I-mode in tokamak EAST. Sci. Adv. 9, eabq5273 (2023).","journal-title":"Sci. Adv."},{"key":"7024_CR10","doi-asserted-by":"publisher","first-page":"042026","DOI":"10.1088\/1741-4326\/ac47b4","volume":"62","author":"J Mailloux","year":"2022","unstructured":"Mailloux, J. et al. Overview of jet results for optimising ITER operation. Nucl. Fusion 62, 042026 (2022).","journal-title":"Nucl. Fusion"},{"key":"7024_CR11","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1038\/d41586-022-00391-1","volume":"602","author":"E Gibney","year":"2022","unstructured":"Gibney, E. Nuclear-fusion reactor smashes energy record. Nature 602, 371 (2022).","journal-title":"Nature"},{"key":"7024_CR12","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1088\/0029-5515\/47\/6\/S01","volume":"47","author":"M Shimada","year":"2007","unstructured":"Shimada, M. et al. Progress in the ITER physics basis\u2014chapter 1: overview and summary. Nucl. Fusion 47, S1 (2007).","journal-title":"Nucl. Fusion"},{"key":"7024_CR13","doi-asserted-by":"publisher","first-page":"A135","DOI":"10.1088\/0741-3335\/37\/11A\/009","volume":"37","author":"FC Schuller","year":"1995","unstructured":"Schuller, F. C. Disruptions in tokamaks. Plasma Phys. Control. Fusion 37, A135 (1995).","journal-title":"Plasma Phys. Control. Fusion"},{"key":"7024_CR14","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1038\/s41586-019-1116-4","volume":"568","author":"J Kates-Harbeck","year":"2019","unstructured":"Kates-Harbeck, J., Svyatkovskiy, A. & Tang, W. Predicting disruptive instabilities in controlled fusion plasmas through deep learning. Nature 568, 526\u2013531 (2019).","journal-title":"Nature"},{"key":"7024_CR15","doi-asserted-by":"publisher","first-page":"741","DOI":"10.1038\/s41567-022-01602-2","volume":"18","author":"J Vega","year":"2022","unstructured":"Vega, J. et al. Disruption prediction with artificial intelligence techniques in tokamak plasmas. Nat. Phys. 18, 741\u2013750 (2022).","journal-title":"Nat. Phys."},{"key":"7024_CR16","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.jnucmat.2014.10.075","volume":"463","author":"M Lehnen","year":"2015","unstructured":"Lehnen, M. et al. Disruptions in ITER and strategies for their control and mitigation. J. Nucl. Mater. 463, 39\u201348 (2015).","journal-title":"J. Nucl. Mater."},{"key":"7024_CR17","doi-asserted-by":"publisher","first-page":"022501","DOI":"10.1063\/1.5125581","volume":"27","author":"Y Fu","year":"2020","unstructured":"Fu, Y. et al. Machine learning control for disruption and tearing mode avoidance. Phys. Plasmas 27, 022501 (2020).","journal-title":"Phys. Plasmas"},{"key":"7024_CR18","doi-asserted-by":"publisher","first-page":"053018","DOI":"10.1088\/0029-5515\/51\/5\/053018","volume":"51","author":"P de Vries","year":"2011","unstructured":"de Vries, P. et al. Survey of disruption causes at jet. Nucl. Fusion 51, 053018 (2011).","journal-title":"Nucl. Fusion"},{"key":"7024_CR19","doi-asserted-by":"publisher","first-page":"106043","DOI":"10.1088\/1741-4326\/aadbb5","volume":"58","author":"F Turco","year":"2018","unstructured":"Turco, F. et al. The causes of the disruptive tearing instabilities of the ITER baseline scenario in DIII-D. Nucl. Fusion 58, 106043 (2018).","journal-title":"Nucl. Fusion"},{"key":"7024_CR20","doi-asserted-by":"publisher","first-page":"055501","DOI":"10.1063\/1.2180747","volume":"13","author":"RJ La Haye","year":"2006","unstructured":"La Haye, R. J. Neoclassical tearing modes and their control. Phys. Plasmas 13, 055501 (2006).","journal-title":"Phys. Plasmas"},{"key":"7024_CR21","doi-asserted-by":"publisher","first-page":"1242","DOI":"10.1103\/PhysRevLett.85.1242","volume":"85","author":"G Gantenbein","year":"2000","unstructured":"Gantenbein, G. et al. Complete suppression of neoclassical tearing modes with current drive at the electron-cyclotron-resonance frequency in ASDEX upgrade tokamak. Phys. Rev. Lett. 85, 1242\u20131245 (2000).","journal-title":"Phys. Rev. Lett."},{"key":"7024_CR22","doi-asserted-by":"publisher","first-page":"2051","DOI":"10.1063\/1.1456066","volume":"9","author":"RJ La Haye","year":"2002","unstructured":"La Haye, R. J. et al. Control of neoclassical tearing modes in DIII-D. Phys. Plasmas 9, 2051\u20132060 (2002).","journal-title":"Phys. Plasmas"},{"key":"7024_CR23","doi-asserted-by":"publisher","first-page":"102502","DOI":"10.1063\/1.3232325","volume":"16","author":"FAG Volpe","year":"2009","unstructured":"Volpe, F. A. G. et al. Advanced techniques for neoclassical tearing mode control in DIII-D. Phys. Plasmas 16, 102502 (2009).","journal-title":"Phys. Plasmas"},{"key":"7024_CR24","doi-asserted-by":"publisher","first-page":"074001","DOI":"10.1088\/0029-5515\/52\/7\/074001","volume":"52","author":"F Felici","year":"2012","unstructured":"Felici, F. et al. Integrated real-time control of MHD instabilities using multi-beam ECRH\/ECCD systems on TCV. Nucl. Fusion 52, 074001 (2012).","journal-title":"Nucl. Fusion"},{"key":"7024_CR25","doi-asserted-by":"publisher","first-page":"074007","DOI":"10.1088\/0029-5515\/52\/7\/074007","volume":"52","author":"M Maraschek","year":"2012","unstructured":"Maraschek, M. Control of neoclassical tearing modes. Nucl. Fusion 52, 074007 (2012).","journal-title":"Nucl. Fusion"},{"key":"7024_CR26","doi-asserted-by":"publisher","first-page":"073020","DOI":"10.1088\/0029-5515\/54\/7\/073020","volume":"54","author":"E Kolemen","year":"2014","unstructured":"Kolemen, E. et al. State-of-the-art neoclassical tearing mode control in DIII-D using real-time steerable electron cyclotron current drive launchers. Nucl. Fusion 54, 073020 (2014).","journal-title":"Nucl. Fusion"},{"key":"7024_CR27","doi-asserted-by":"publisher","first-page":"016042","DOI":"10.1088\/1741-4326\/aa95d1","volume":"58","author":"M Park","year":"2017","unstructured":"Park, M., Na, Y.-S., Seo, J., Kim, M. & Kim, K. Effect of electron cyclotron beam width to neoclassical tearing mode stabilization by minimum seeking control in iter. Nucl. Fusion 58, 016042 (2017).","journal-title":"Nucl. Fusion"},{"key":"7024_CR28","doi-asserted-by":"publisher","first-page":"055002","DOI":"10.1103\/PhysRevLett.127.055002","volume":"127","author":"L Bard\u00f3czi","year":"2021","unstructured":"Bard\u00f3czi, L., Logan, N. C. & Strait, E. J. Neoclassical tearing mode seeding by nonlinear three-wave interactions in tokamaks. Phys. Rev. Lett. 127, 055002 (2021).","journal-title":"Phys. Rev. Lett."},{"key":"7024_CR29","doi-asserted-by":"publisher","first-page":"026015","DOI":"10.1088\/1741-4326\/ac3e3a","volume":"62","author":"S Zeng","year":"2022","unstructured":"Zeng, S., Zhu, P., Izzo, V., Li, H. & Jiang, Z. MHD simulations of cold bubble formation from 2\/1 tearing mode during massive gas injection in a tokamak. Nucl. Fusion 62, 026015 (2022).","journal-title":"Nucl. Fusion"},{"key":"7024_CR30","doi-asserted-by":"publisher","first-page":"066001","DOI":"10.1088\/1741-4326\/acc750","volume":"63","author":"X Yang","year":"2023","unstructured":"Yang, X., Liu, Y., Xu, W., He, Y. & Xia, G. Effect of negative triangularity on tearing mode stability in tokamak plasmas. Nucl. Fusion 63, 066001 (2023).","journal-title":"Nucl. Fusion"},{"key":"7024_CR31","doi-asserted-by":"publisher","first-page":"066022","DOI":"10.1088\/1741-4326\/ab1571","volume":"59","author":"T Wakatsuki","year":"2019","unstructured":"Wakatsuki, T., Suzuki, T., Hayashi, N., Oyama, N. & Ide, S. Safety factor profile control with reduced central solenoid flux consumption during plasma current ramp-up phase using a reinforcement learning technique. Nucl. Fusion 59, 066022 (2019).","journal-title":"Nucl. Fusion"},{"key":"7024_CR32","doi-asserted-by":"publisher","first-page":"106010","DOI":"10.1088\/1741-4326\/ac121b","volume":"61","author":"J Seo","year":"2021","unstructured":"Seo, J. et al. Feedforward beta control in the KSTAR tokamak by deep reinforcement learning. Nucl. Fusion 61, 106010 (2021).","journal-title":"Nucl. Fusion"},{"key":"7024_CR33","unstructured":"Char, I. et al. Offline model-based reinforcement learning for tokamak control. In 2023 Learning for Dynamics and Control Conference (L4DC) 1357\u20131372 (PMLR, 2023)."},{"key":"7024_CR34","doi-asserted-by":"publisher","first-page":"076017","DOI":"10.1088\/1741-4326\/acd393","volume":"63","author":"T Wakatsuki","year":"2023","unstructured":"Wakatsuki, T., Yoshida, M., Narita, E., Suzuki, T. & Hayashi, N. Simultaneous control of safety factor profile and normalized beta for JT-60SA using reinforcement learning. Nucl. Fusion 63, 076017 (2023).","journal-title":"Nucl. Fusion"},{"key":"7024_CR35","doi-asserted-by":"publisher","first-page":"114161","DOI":"10.1016\/j.fusengdes.2024.114161","volume":"200","author":"B. D. Tracey","year":"2024","unstructured":"Tracey, B. D. et al. Towards practical reinforcement learning for tokamak magnetic control.\u00a0Fusion Eng. Des.\u00a0200, 114161 (2024).","journal-title":"Fusion Eng. Des"},{"key":"7024_CR36","unstructured":"Shousha, R. et al. Improved real-time equilibrium reconstruction with kinetic constraints on DIII-D and NSTX-U. In 64th Annual Meeting of the APS Division of Plasma Physics Vol. 67, PP11.00011 (APS, 2022); https:\/\/meetings.aps.org\/Meeting\/DPP22\/Session\/PP11.11."},{"key":"7024_CR37","doi-asserted-by":"crossref","unstructured":"Shousha, R. et al. Machine learning-based real-time kinetic profile reconstruction in DIII-D. Nucl. Fusion 64, 026006 (2024).","DOI":"10.1088\/1741-4326\/ad142f"},{"key":"7024_CR38","doi-asserted-by":"publisher","first-page":"2630","DOI":"10.1109\/TNNLS.2021.3085504","volume":"33","author":"A Jalalvand","year":"2022","unstructured":"Jalalvand, A., Abbate, J., Conlin, R., Verdoolaege, G. & Kolemen, E. Real-time and adaptive reservoir computing with application to profile prediction in fusion plasma. IEEE Trans. Neural Netw. Learn. Syst. 33, 2630\u20132641 (2022).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"7024_CR39","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.1088\/0029-5515\/38\/7\/308","volume":"38","author":"J Ferron","year":"1998","unstructured":"Ferron, J. et al. Real time equilibrium reconstruction for tokamak discharge control. Nucl. Fusion 38, 1055 (1998).","journal-title":"Nucl. Fusion"},{"key":"7024_CR40","doi-asserted-by":"publisher","first-page":"056008","DOI":"10.1088\/1741-4326\/ab0762","volume":"59","author":"M Boyer","year":"2019","unstructured":"Boyer, M., Kaye, S. & Erickson, K. Real-time capable modeling of neutral beam injection on NSTX-U using neural networks. Nucl. Fusion 59, 056008 (2019).","journal-title":"Nucl. Fusion"},{"key":"7024_CR41","doi-asserted-by":"publisher","first-page":"126019","DOI":"10.1088\/1741-4326\/ac2d56","volume":"61","author":"J Barr","year":"2021","unstructured":"Barr, J. et al. Development and experimental qualification of novel disruption prevention techniques on DIII-D. Nucl. Fusion 61, 126019 (2021).","journal-title":"Nucl. Fusion"},{"key":"7024_CR42","doi-asserted-by":"publisher","first-page":"046027","DOI":"10.1088\/1741-4326\/abe08d","volume":"61","author":"J Abbate","year":"2021","unstructured":"Abbate, J., Conlin, R. & Kolemen, E. Data-driven profile prediction for DIII-D. Nucl. Fusion 61, 046027 (2021).","journal-title":"Nucl. Fusion"},{"key":"7024_CR43","doi-asserted-by":"crossref","unstructured":"Seo, J. Solving real-world optimization tasks using physics-informed neural computing. Sci. Rep. 14, 202 (2024).","DOI":"10.1038\/s41598-023-49977-3"},{"key":"7024_CR44","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-34092-0","volume":"13","author":"Y-S Na","year":"2022","unstructured":"Na, Y.-S. et al. Observation of a new type of self-generated current in magnetized plasmas. Nat. Commun. 13, 6477 (2022).","journal-title":"Nat. Commun."},{"key":"7024_CR45","doi-asserted-by":"publisher","first-page":"4901","DOI":"10.1063\/1.1143545","volume":"63","author":"TN Carlstrom","year":"1992","unstructured":"Carlstrom, T. N. et al. Design and operation of the multipulse Thomson scattering diagnostic on DIII-D (invited). Rev. Sci. Instrum. 63, 4901\u20134906 (1992).","journal-title":"Rev. Sci. Instrum."},{"key":"7024_CR46","doi-asserted-by":"publisher","first-page":"2012","DOI":"10.1063\/1.1138774","volume":"57","author":"RP Seraydarian","year":"1986","unstructured":"Seraydarian, R. P. & Burrell, K. H. Multichordal charge-exchange recombination spectroscopy on the DIII-D tokamak. Rev. Sci. Instrum. 57, 2012\u20132014 (1986).","journal-title":"Rev. Sci. Instrum."},{"key":"7024_CR47","doi-asserted-by":"publisher","first-page":"111368","DOI":"10.1016\/j.fusengdes.2019.111368","volume":"150","author":"M Margo","year":"2020","unstructured":"Margo, M. et al. Current state of DIII-D plasma control system. Fusion Eng. Des. 150, 111368 (2020).","journal-title":"Fusion Eng. Des."},{"key":"7024_CR48","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1016\/j.physleta.2004.02.010","volume":"323","author":"D Escande","year":"2004","unstructured":"Escande, D. & Ottaviani, M. Simple and rigorous solution for the nonlinear tearing mode. Phys. Lett. A 323, 278\u2013284 (2004).","journal-title":"Phys. Lett. A"},{"key":"7024_CR49","doi-asserted-by":"publisher","first-page":"070701","DOI":"10.1063\/5.0009110","volume":"27","author":"J Loizu","year":"2020","unstructured":"Loizu, J. et al. Direct prediction of nonlinear tearing mode saturation using a variational principle. Phys. Plasmas 27, 070701 (2020).","journal-title":"Phys. Plasmas"},{"key":"7024_CR50","doi-asserted-by":"publisher","first-page":"095003","DOI":"10.1103\/PhysRevLett.107.095003","volume":"107","author":"M Muraglia","year":"2011","unstructured":"Muraglia, M. et al. Generation and amplification of magnetic islands by drift interchange turbulence. Phys. Rev. Lett. 107, 095003 (2011).","journal-title":"Phys. Rev. Lett."},{"key":"7024_CR51","doi-asserted-by":"publisher","first-page":"054018","DOI":"10.1088\/0741-3335\/57\/5\/054018","volume":"57","author":"WA Hornsby","year":"2015","unstructured":"Hornsby, W. A. et al. On seed island generation and the non-linear self-consistent interaction of the tearing mode with electromagnetic gyro-kinetic turbulence. Plasma Phys. Control. Fusion 57, 054018 (2015).","journal-title":"Plasma Phys. Control. Fusion"},{"key":"7024_CR52","doi-asserted-by":"publisher","first-page":"042308","DOI":"10.1063\/1.4981229","volume":"24","author":"O Agullo","year":"2017","unstructured":"Agullo, O. et al. Nonlinear dynamics of turbulence driven magnetic islands. I. Theoretical aspects. Phys. Plasmas 24, 042308 (2017).","journal-title":"Phys. Plasmas"},{"key":"7024_CR53","doi-asserted-by":"publisher","first-page":"225001","DOI":"10.1103\/PhysRevLett.128.225001","volume":"128","author":"GJ Choi","year":"2022","unstructured":"Choi, G. J. & Hahm, T. S. Long term vortex flow evolution around a magnetic island in tokamaks. Phys. Rev. Lett. 128, 225001 (2022).","journal-title":"Phys. Rev. Lett."},{"key":"7024_CR54","doi-asserted-by":"publisher","first-page":"1999","DOI":"10.1088\/0741-3335\/44\/9\/315","volume":"44","author":"O Sauter","year":"2002","unstructured":"Sauter, O. et al. Marginal \u03b2-limit for neoclassical tearing modes in JET H-mode discharges. Plasma Phys. Control. Fusion 44, 1999 (2002).","journal-title":"Plasma Phys. Control. Fusion"},{"key":"7024_CR55","unstructured":"Brockman, G. et al. OpenAI Gym. Preprint at https:\/\/arxiv.org\/abs\/1606.01540 (2016)."},{"key":"7024_CR56","unstructured":"Lillicrap, T. P. et al. Continuous control with deep reinforcement learning. Preprint at https:\/\/arxiv.org\/abs\/1509.02971 (2015)."},{"key":"7024_CR57","unstructured":"keras-rl2. GitHub https:\/\/github.com\/inarikami\/keras-rl2 (2019)."},{"key":"7024_CR58","doi-asserted-by":"publisher","first-page":"104182","DOI":"10.1016\/j.engappai.2021.104182","volume":"100","author":"R Conlin","year":"2021","unstructured":"Conlin, R., Erickson, K., Abbate, J. & Kolemen, E. Keras2c: a library for converting Keras neural networks to real-time compatible C. Eng. App. Artif. Intell. 100, 104182 (2021).","journal-title":"Eng. App. Artif. Intell."}],"container-title":["Nature"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41586-024-07024-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-024-07024-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-024-07024-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,21]],"date-time":"2024-02-21T12:05:37Z","timestamp":1708517137000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41586-024-07024-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,21]]},"references-count":58,"journal-issue":{"issue":"8000","published-print":{"date-parts":[[2024,2,22]]}},"alternative-id":["7024"],"URL":"https:\/\/doi.org\/10.1038\/s41586-024-07024-9","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-3163842\/v1","asserted-by":"object"}]},"ISSN":["0028-0836","1476-4687"],"issn-type":[{"value":"0028-0836","type":"print"},{"value":"1476-4687","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,21]]},"assertion":[{"value":"12 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}