{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T06:39:47Z","timestamp":1787726387975,"version":"build-2784847793"},"reference-count":44,"publisher":"Informa UK Limited","issue":"1","content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Control"],"published-print":{"date-parts":[[2026,1,2]]},"DOI":"10.1080\/00207179.2025.2497894","type":"journal-article","created":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T22:30:26Z","timestamp":1746052226000},"page":"98-110","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":4,"title":["Output feedback linear quadratic regulator design through one-shot Q-function learning"],"prefix":"10.1080","volume":"99","author":[{"given":"Ahmad","family":"Pishro Asl","sequence":"first","affiliation":[{"name":"Sahand University of Technology","place":["Tabriz, Iran"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmad","family":"Akbari","sequence":"additional","affiliation":[{"name":"Sahand University of Technology","place":["Tabriz, Iran"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2025,4,30]]},"reference":[{"key":"e_1_3_4_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107090"},{"key":"e_1_3_4_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1994.735224"},{"key":"e_1_3_4_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-69082-7"},{"key":"e_1_3_4_5_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2017.1312669"},{"key":"e_1_3_4_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2023.3315651"},{"key":"e_1_3_4_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2023.3237200"},{"key":"e_1_3_4_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.110060"},{"key":"e_1_3_4_9_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2024.2305727"},{"key":"e_1_3_4_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1971.1099755"},{"key":"e_1_3_4_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2024.104659"},{"issue":"12","key":"e_1_3_4_12_1","first-page":"1993","article-title":"Direct adaptive optimal control for uncertain continuous-time LTI systems without persistence of excitation","volume":"65","author":"Jha S. K.","year":"2018","unstructured":"Jha, S. K., Roy, S. B., & Bhasin, S. (2018). Direct adaptive optimal control for uncertain continuous-time LTI systems without persistence of excitation. IEEE Transactions on Circuits and Systems II: Express Briefs, 65(12), 1993\u20131997.","journal-title":"IEEE Transactions on Circuits and Systems II: Express Briefs"},{"key":"e_1_3_4_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"e_1_3_4_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1968.1098829"},{"key":"e_1_3_4_15_1","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198537953.001.0001"},{"key":"e_1_3_4_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.9"},{"key":"e_1_3_4_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3207510"},{"key":"e_1_3_4_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2010.2043839"},{"key":"e_1_3_4_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631"},{"key":"e_1_3_4_20_1","unstructured":"Lim R. K. Phan M. Q. & Longman R. W. (1998). State estimation with ARMarkov models (Department of Mechanical and Aerospace Engineering Technical Report 3046)."},{"key":"e_1_3_4_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50815-3"},{"key":"e_1_3_4_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2477810"},{"key":"e_1_3_4_23_1","doi-asserted-by":"publisher","DOI":"10.1201\/9781315214429"},{"key":"e_1_3_4_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17122"},{"key":"e_1_3_4_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3172250"},{"key":"e_1_3_4_26_1","unstructured":"Park Y. Rossi R. Wen Z. Wu G. & Zhao H. (2020). Structured policy iteration for linear quadratic regulator. In Proceedings of the 37th International Conference on Machine Learning (pp. 7521\u20137531). PMLR."},{"key":"e_1_3_4_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106785"},{"key":"e_1_3_4_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2616644"},{"key":"e_1_3_4_29_1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470182963"},{"key":"e_1_3_4_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.5962385"},{"key":"e_1_3_4_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-15858-2"},{"key":"e_1_3_4_32_1","unstructured":"Tu S. & Recht B. (2018). Least-squares temporal difference learning for the linear quadratic regulator. In Proceedings of the 35th International Conference on Machine Learning (pp. 5005\u20135014).\u00a0PMLR."},{"key":"e_1_3_4_33_1","unstructured":"Umenberger J. & Sch\u00f6n T. B. (2018). Learning convex bounds for linear quadratic control policy synthesis. In Proceedings of the 32nd International Conference on Neural Information Processing Systems (NeurIPS 2018)\u00a0(pp. 9584\u20139595). Curran Associates Inc."},{"key":"e_1_3_4_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.018"},{"key":"e_1_3_4_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927523"},{"key":"e_1_3_4_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/MED.2009.5164743"},{"key":"e_1_3_4_37_1","doi-asserted-by":"publisher","DOI":"10.1049\/PBCE081E"},{"key":"e_1_3_4_38_1","unstructured":"Watkins C. J. C. H. (1989). Learning from delayed rewards."},{"key":"e_1_3_4_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"e_1_3_4_40_1","doi-asserted-by":"crossref","unstructured":"Webros P. J. (1990). A menu of designs for reinforcement learning over time. In W. T. Miller R. S. Sutton & P. J. Werbos (Eds.)\u00a0Neural networks for control (pp. 67\u201395). MIT Press.","DOI":"10.7551\/mitpress\/4939.003.0007"},{"key":"e_1_3_4_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1989.70114"},{"key":"e_1_3_4_42_1","unstructured":"Werbos P. J. (1992). Approximate dynamic programming for real-time control and neural modeling. In D. A. White & D. A. Sofge (Eds.) \u00a0Handbook of intelligent control (pp. 493\u2013525).\u00a0Van Nostrand Reinhold."},{"key":"e_1_3_4_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2004.09.003"},{"key":"e_1_3_4_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3098985"},{"key":"e_1_3_4_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.105833"}],"container-title":["International Journal of Control"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/00207179.2025.2497894","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T12:49:43Z","timestamp":1770727783000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/00207179.2025.2497894"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,30]]},"references-count":44,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,2]]}},"alternative-id":["10.1080\/00207179.2025.2497894"],"URL":"https:\/\/doi.org\/10.1080\/00207179.2025.2497894","relation":{},"ISSN":["0020-7179","1366-5820"],"issn-type":[{"value":"0020-7179","type":"print"},{"value":"1366-5820","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,30]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tcon20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tcon20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2024-05-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-21","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}