{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T07:23:57Z","timestamp":1772781837514,"version":"3.50.1"},"reference-count":28,"publisher":"Informa UK Limited","issue":"16","funder":[{"DOI":"10.13039\/501100001691","name":"JSPS","doi-asserted-by":"publisher","award":["JP21H04875"],"award-info":[{"award-number":["JP21H04875"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Advanced Robotics"],"published-print":{"date-parts":[[2023,8,18]]},"DOI":"10.1080\/01691864.2023.2229886","type":"journal-article","created":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T18:39:38Z","timestamp":1688409578000},"page":"1012-1024","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":3,"title":["Deep reinforcement learning for continuous-time self-triggered control with experimental evaluation"],"prefix":"10.1080","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2521-8589","authenticated-orcid":false,"given":"Ran","family":"Wang","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Kyoto University, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2963-2584","authenticated-orcid":false,"given":"Kenji","family":"Kashima","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Kyoto University, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","published-online":{"date-parts":[[2023,7,3]]},"reference":[{"key":"CIT0001","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"CIT0002","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"CIT0003","volume-title":"Reinforcement learning: an introduction","author":"Sutton RS","year":"2018"},{"key":"CIT0004","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, et\u00a0al. Continuous control with deep reinforcement learning. arXiv preprint arXiv:150902971. 2015."},{"key":"CIT0005","unstructured":"Fujimoto S, Hoof H, Meger D. Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning; 2018. p. 1582\u20131591."},{"key":"CIT0006","unstructured":"Haarnoja T, Zhou A, Abbeel P, et\u00a0al. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International conference on machine learning; PMLR; 2018. p. 1861\u20131870."},{"key":"CIT0007","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.41"},{"key":"CIT0008","volume-title":"Optimal sampled-data control systems","author":"Chen T","year":"2012"},{"key":"CIT0009","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6425820"},{"key":"CIT0010","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619335"},{"key":"CIT0011","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.03.013"},{"key":"CIT0012","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.02.030"},{"key":"CIT0013","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814657"},{"key":"CIT0014","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2980048"},{"key":"CIT0015","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2012.2206719"},{"key":"CIT0016","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2021.10.353"},{"key":"CIT0017","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"CIT0018","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"CIT0019","unstructured":"Degris T, White M, Sutton R. Off-policy actor-critic. In: International Conference on Machine Learning; 2012."},{"key":"CIT0020","unstructured":"Sutton RS, McAllester D, Singh S, et\u00a0al. Policy gradient methods for reinforcement learning with function approximation. In: Solla S, Leen T, M\u00fcller K, editors. Advances in Neural Information Processing Systems; Vol. 12, MIT Press; 1999. https:\/\/proceedings.neurips.cc\/paper\/1999\/file\/464d828b85b0bed98e80ade0a5c43b0f-Paper.pdf."},{"key":"CIT0021","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11631"},{"key":"CIT0022","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"CIT0023","unstructured":"Silver D, Lever G, Heess N, et\u00a0al. Deterministic policy gradient algorithms. In: International conference on machine learning; PMLR; 2014. p. 387\u2013395."},{"key":"CIT0024","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"CIT0025","volume-title":"Deep learning toolbox reference","author":"Mark HB","year":"2021"},{"key":"CIT0026","unstructured":"Gallou\u00e9dec Q, Cazin N, Dellandr\u00e9a E, et\u00a0al. panda-gym: Open-source goal-conditioned environments for robotic learning. 4th Robot Learning Workshop: Self-Supervised and Lifelong Learning at NeurIPS. 2021."},{"key":"CIT0027","author":"Andrychowicz M","year":"2017","journal-title":"arXiv preprint arXiv:1707.01495"},{"key":"CIT0028","volume-title":"Quanser rotary pendulum workbook","author":"Jacob A","year":"2011"}],"container-title":["Advanced Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/01691864.2023.2229886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T05:27:43Z","timestamp":1691731663000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/01691864.2023.2229886"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,3]]},"references-count":28,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2023,8,18]]}},"alternative-id":["10.1080\/01691864.2023.2229886"],"URL":"https:\/\/doi.org\/10.1080\/01691864.2023.2229886","relation":{},"ISSN":["0169-1864","1568-5535"],"issn-type":[{"value":"0169-1864","type":"print"},{"value":"1568-5535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,3]]},"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=tadr20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2022-12-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-06-19","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-07-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}