{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T06:20:21Z","timestamp":1788502821938,"version":"build-2803163510"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T00:00:00Z","timestamp":1774915200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T00:00:00Z","timestamp":1774915200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Prevention and Control of Emerging and Major Infectious Diseases-National Science and Technology Major Project","award":["No.2025ZD01900100"],"award-info":[{"award-number":["No.2025ZD01900100"]}]},{"name":"Prevention and Control of Emerging and Major Infectious Diseases-National Science and Technology Major Project","award":["No.2025ZD01900100"],"award-info":[{"award-number":["No.2025ZD01900100"]}]},{"name":"Prevention and Control of Emerging and Major Infectious Diseases-National Science and Technology Major Project","award":["No.2025ZD01900100"],"award-info":[{"award-number":["No.2025ZD01900100"]}]},{"name":"Prevention and Control of Emerging and Major Infectious Diseases-National Science and Technology Major Project","award":["No.2025ZD01900100"],"award-info":[{"award-number":["No.2025ZD01900100"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-39377-8","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T09:52:58Z","timestamp":1774950778000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Optimization of infectious disease intervention measures using reinforcement learning with UK COVID-19 epidemic data"],"prefix":"10.1038","volume":"16","author":[{"given":"Baida","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yakai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huichun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenghu","family":"Zu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,31]]},"reference":[{"key":"39377_CR1","unstructured":"WHO. Coronavirus (COVID-19) dashboard. (2025). https:\/\/covid19.who.int"},{"key":"39377_CR2","unstructured":"US Centers for Disease Control and Prevention. COVID data tracker. (2025). https:\/\/covid.cdc.gov\/covid-data-tracker"},{"key":"39377_CR3","doi-asserted-by":"publisher","first-page":"1303","DOI":"10.1038\/s41562-020-01009-0","volume":"4","author":"N Haug","year":"2020","unstructured":"Haug, N. et al. Ranking the effectiveness of worldwide COVID-19 government interventions. Nat. Hum. Behav. 4, 1303\u20131312 (2020).","journal-title":"Nat. Hum. Behav."},{"key":"39377_CR4","doi-asserted-by":"publisher","unstructured":"Djidjou\u2013Demasse, R., Michalakis, Y., Choisy, M., Sofonea, M. T. & Alizon, S. Optimal COVID-19 epidemic control until vaccine deployment. Preprint at https:\/\/medrxiv.org\/content\/ (2020). https:\/\/doi.org\/10.1101\/2020.04.02.20049189v1","DOI":"10.1101\/2020.04.02.20049189v1"},{"key":"39377_CR5","doi-asserted-by":"publisher","first-page":"3560","DOI":"10.1038\/s41467-021-23865-8","volume":"12","author":"B Yang","year":"2021","unstructured":"Yang, B. et al. Effect of specific non-pharmaceutical intervention policies on SARS-CoV-2 transmission in the counties of the united States. Nat. Commun. 12, 3560 (2021).","journal-title":"Nat. Commun."},{"key":"39377_CR6","doi-asserted-by":"publisher","first-page":"e488","DOI":"10.1016\/S2214-109X(20)30074-7","volume":"8","author":"J Hellewell","year":"2020","unstructured":"Hellewell, J. et al. Feasibility of controlling COVID-19 outbreaks by isolation of cases and contacts. Lancet Glob Health. 8, e488\u2013e496 (2020).","journal-title":"Lancet Glob Health"},{"key":"39377_CR7","doi-asserted-by":"crossref","unstructured":"Kermack, W. O. & McKendrick, A. G. A contribution to the mathematical theory of epidemics. Proc. R. Soc. Lond. A 115, 700\u2013721 (1927).","DOI":"10.1098\/rspa.1927.0118"},{"key":"39377_CR8","doi-asserted-by":"publisher","first-page":"940","DOI":"10.1186\/1471-2458-13-940","volume":"13","author":"JJ Grefenstette","year":"2013","unstructured":"Grefenstette, J. J. et al. FRED (A framework for reconstructing epidemic Dynamics): an open-source software system for modeling infectious diseases and control strategies using census-based populations. BMC Public. Health. 13, 940 (2013).","journal-title":"BMC Public. Health"},{"key":"39377_CR9","doi-asserted-by":"publisher","first-page":"e1009149","DOI":"10.1371\/journal.pcbi.1009149","volume":"17","author":"CC Kerr","year":"2021","unstructured":"Kerr, C. C. et al. Covasim: an agent-based model of COVID-19 dynamics and interventions. PLoS Comput. Biol. 17, e1009149 (2021).","journal-title":"PLoS Comput. Biol."},{"key":"39377_CR10","doi-asserted-by":"crossref","unstructured":"AlMahamid, F. & Grolinger, K. Reinforcement learning algorithms: an overview and classification. IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), 1\u20137 (2021).","DOI":"10.1109\/CCECE53047.2021.9569056"},{"key":"39377_CR11","unstructured":"Kuzmin, V. Connectionist Q-learning in robot control task. Proc. Riga. Tech. Univ. 5 (2002)."},{"key":"39377_CR12","unstructured":"Fujimoto, S., Hoof, H. & Meger, D. Addressing function approximation error in actor-critic methods. In Proceedings of the Thirty-Fifth International Conference on Machine Learning 1587\u20131596 (2018)."},{"key":"39377_CR13","doi-asserted-by":"publisher","first-page":"26549","DOI":"10.1109\/ACCESS.2020.2971172","volume":"8","author":"A Anwar","year":"2020","unstructured":"Anwar, A. & Raychowdhury, A. Autonomous navigation via deep reinforcement learning for resource constraint edge nodes using transfer learning. IEEE Access. 8, 26549\u201326560 (2020).","journal-title":"IEEE Access."},{"key":"39377_CR14","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":"39377_CR15","unstructured":"Lillicrap, T. P. et al. Continuous control with deep reinforcement learning. Preprint at (2015). https:\/\/arxiv.org\/abs\/1509.02971"},{"key":"39377_CR16","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A. & Klimov, O. Proximal policy optimization algorithms. Preprint at (2017). https:\/\/arxiv.org\/abs\/1707.06347"},{"key":"39377_CR17","first-page":"2778","volume":"PMLR","author":"D Pathak","year":"2017","unstructured":"Pathak, D., Agrawal, P., Efros, A. A. & Darrell, T. Curiosity-driven exploration by self-supervised prediction. Int. Conf. Mach. Learn. PMLR, 2778\u20132787 (2017).","journal-title":"Int. Conf. Mach. Learn."},{"key":"39377_CR18","unstructured":"Kulkarni, T. D., Narasimhan, K., Saeedi, A. & Tenenbaum, J. Hierarchical deep reinforcement learning: integrating Temporal abstraction and intrinsic motivation. In Proceedings of the 30th International Conference on Neural Information Processing Systems 3682-3690 (2016)."},{"key":"39377_CR19","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P. & Levine, S. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In Proceedings of the Thirty-Fifth International Conference on Machine Learning 1856\u20131865 (2018)."},{"key":"39377_CR20","doi-asserted-by":"crossref","unstructured":"Karin, O. et al. Adaptive cyclic exit strategies from lockdown to suppress COVID-19 and allow economic activity. medRxiv 2020, 04 (2020).","DOI":"10.1101\/2020.04.04.20053579"},{"key":"39377_CR21","doi-asserted-by":"publisher","first-page":"1366","DOI":"10.1016\/j.ejor.2022.06.034","volume":"305","author":"NFD Huberts","year":"2023","unstructured":"Huberts, N. F. D. & Thijssen, J. J. J. Optimal timing of non-pharmaceutical interventions during an epidemic. Eur. J. Oper. Res. 305, 1366\u20131389 (2023).","journal-title":"Eur. J. Oper. Res."},{"key":"39377_CR22","doi-asserted-by":"publisher","first-page":"964","DOI":"10.1038\/s41562-020-0931-9","volume":"4","author":"A Aleta","year":"2020","unstructured":"Aleta, A. et al. Modelling the impact of testing, contact tracing and household quarantine on second waves of COVID-19. Nat. Hum. Behav. 4, 964\u2013971 (2020).","journal-title":"Nat. Hum. Behav."},{"key":"39377_CR23","doi-asserted-by":"publisher","first-page":"3319","DOI":"10.1038\/s41467-022-30642-8","volume":"13","author":"A Ash","year":"2022","unstructured":"Ash, A., Bento, A. M., Kaffine, D., Rao, A. & Bento A. I. Disease-economy trade-offs under alternative epidemic control strategies. Nat. Commun. 13, 3319 (2022).","journal-title":"Nat. Commun."},{"key":"39377_CR24","doi-asserted-by":"publisher","first-page":"105919","DOI":"10.1016\/j.cor.2022.105919","volume":"146","author":"M Kaleta","year":"2022","unstructured":"Kaleta, M. et al. Long-term spatial and population-structured planning of non-pharmaceutical interventions to epidemic outbreaks. Comput. Oper. Res. 146, 105919 (2022).","journal-title":"Comput. Oper. Res."},{"key":"39377_CR25","doi-asserted-by":"publisher","first-page":"102676","DOI":"10.1016\/j.bspc.2021.102676","volume":"68","author":"R Padmanabhan","year":"2021","unstructured":"Padmanabhan, R., Meskin, N., Khattab, T., Shraim, M. & Al-Hitmi, M. Reinforcement learning-based decision support system for COVID-19. Biomed. Signal. Process. Control. 68, 102676 (2021).","journal-title":"Biomed. Signal. Process. Control"},{"key":"39377_CR26","doi-asserted-by":"publisher","first-page":"e0251550","DOI":"10.1371\/journal.pone.0251550","volume":"16","author":"GH Kwak","year":"2021","unstructured":"Kwak, G. H., Ling, L. & Hui, P. Deep reinforcement learning approaches for global public health strategies for COVID-19 pandemic. PLoS One. 16, e0251550 (2021).","journal-title":"PLoS One"},{"key":"39377_CR27","unstructured":"Song, S., Zong, Z., Li, Y., Liu, X. & Yu, Y. Reinforced epidemic control: saving both lives and economy. Preprint at (2020). https:\/\/arxiv.org\/abs\/2008.01257"},{"key":"39377_CR28","doi-asserted-by":"crossref","unstructured":"Libin, P. J. et al. Deep reinforcement learning for large-scale epidemic control. In Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases 155\u2013170 (2020).","DOI":"10.1007\/978-3-030-67670-4_10"},{"key":"39377_CR29","unstructured":"Ma, A., Gupta, N., Abouzied, A. & Shasha, D. Planning multiple epidemic interventions with reinforcement learning. Preprint at (2023). https:\/\/arxiv.org\/abs\/2301.12802"},{"key":"39377_CR30","doi-asserted-by":"crossref","unstructured":"Bampa, M., Fasth, T., Magnusson, S. & Papapetrou, P. EpidRLearn: Learning intervention strategies for epidemics with reinforcement learning. In Proceedings of International Conference on Artificial Intelligence in Medicine 189\u2013199 (2022).","DOI":"10.1007\/978-3-031-09342-5_18"},{"key":"39377_CR31","first-page":"1","volume":"17","author":"T Feng","year":"2023","unstructured":"Feng, T., Song, S., Xia, T. & Li, Y. Contact tracing and epidemic intervention via deep reinforcement learning. ACM Trans. Knowl. Discov Data. 17, 1\u201324 (2023).","journal-title":"ACM Trans. Knowl. Discov Data"},{"key":"39377_CR32","doi-asserted-by":"crossref","unstructured":"Feng, T. et al. Precise mobility intervention for epidemic control using unobservable information via deep reinforcement learning. In: Proc. 28th ACM SIGKDD Conf. Knowl. Discov. Data Min., 2882\u20132892 (2022).","DOI":"10.1145\/3534678.3539195"},{"key":"39377_CR33","doi-asserted-by":"publisher","first-page":"22106","DOI":"10.1038\/s41598-020-79147-8","volume":"10","author":"AQ Ohi","year":"2020","unstructured":"Ohi, A. Q., Mridha, M. F., Monowar, M. M. & Abdul Hamid, M. D. Exploring optimal control of epidemic spread using reinforcement learning. Sci. Rep. 10, 22106 (2020).","journal-title":"Sci. Rep."},{"key":"39377_CR34","first-page":"2613","volume":"23","author":"H Hasselt","year":"2010","unstructured":"Hasselt, H. Double Q-learning. Adv. Neural Inf. Process. Syst. 23, 2613\u20132621 (2010).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"39377_CR35","unstructured":"Kompella, V. et al. Reinforcement learning for optimization of COVID-19 mitigation policies. Preprint at (2020). https:\/\/arxiv.org\/abs\/2010.10560"},{"key":"39377_CR36","doi-asserted-by":"publisher","first-page":"2993","DOI":"10.1038\/s41467-021-23276-9","volume":"12","author":"CC Kerr","year":"2021","unstructured":"Kerr, C. C. et al. Controlling COVID-19 via test-trace-quarantine. Nat. Commun. 12, 2993 (2021).","journal-title":"Nat. Commun."},{"key":"39377_CR37","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1016\/S2352-4642(20)30250-9","volume":"4","author":"J Panovska-Griffiths","year":"2020","unstructured":"Panovska-Griffiths, J. et al. Determining the optimal strategy for reopening schools, the impact of test and trace interventions, and the risk of occurrence of a second COVID-19 epidemic wave in the UK: a modelling study. Lancet Child. Adolesc. Health. 4, 817\u2013827 (2020).","journal-title":"Lancet Child. Adolesc. Health"},{"key":"39377_CR38","doi-asserted-by":"publisher","first-page":"e916","DOI":"10.1016\/S2214-109X(21)00103-0","volume":"9","author":"QD Pham","year":"2021","unstructured":"Pham, Q. D. et al. Estimating and mitigating the risk of COVID-19 epidemic rebound associated with reopening of international borders in vietnam: a modelling study. Lancet Glob Health. 9, e916\u2013e924 (2021).","journal-title":"Lancet Glob Health"},{"key":"39377_CR39","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/s10479-022-04926-7","volume":"328","author":"S Bushaj","year":"2023","unstructured":"Bushaj, S., Yin, X., Beqiri, A., Andrew, D. & B\u00fcy\u00fcktahtak\u0131n, I. E. A simulation-deep reinforcement learning (SiRL) approach for epidemic control optimization. Ann. Oper. Res. 328, 245\u2013277 (2023).","journal-title":"Ann. Oper. Res."},{"key":"39377_CR40","unstructured":"Akiba, T. et al. A next-generation hyperparameter optimization framework. In Proc. 25th ACM SIGKDD Int. Conf. Knowl. Discov. Data. Min, 2623\u20132631 (2021)."},{"key":"39377_CR41","unstructured":"Brockman, G. et al. OpenAI Gym. Preprint at (2016). https:\/\/arxiv.org\/abs\/1606.01540"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-39377-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-39377-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-39377-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T09:53:08Z","timestamp":1774950788000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-39377-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,31]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["39377"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-39377-8","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,31]]},"assertion":[{"value":"16 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"10627"}}