{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T23:43:31Z","timestamp":1770335011233,"version":"3.49.0"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92067204"],"award-info":[{"award-number":["92067204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62141604"],"award-info":[{"award-number":["62141604"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61903017"],"award-info":[{"award-number":["61903017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62103015"],"award-info":[{"award-number":["62103015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Defense Science and Technology Key Laboratory Fund Program","award":["6142208200301"],"award-info":[{"award-number":["6142208200301"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for Central Universities of China","doi-asserted-by":"publisher","award":["YWF-20-BJ-J-920"],"award-info":[{"award-number":["YWF-20-BJ-J-920"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. I"],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1109\/tcsi.2022.3163463","type":"journal-article","created":{"date-parts":[[2022,5,26]],"date-time":"2022-05-26T19:36:06Z","timestamp":1653593766000},"page":"2994-3005","source":"Crossref","is-referenced-by-count":6,"title":["Optimizing Constrained Guidance Policy With Minimum Overload Regularization"],"prefix":"10.1109","volume":"69","author":[{"given":"Weilin","family":"Luo","sequence":"first","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Chen","sequence":"additional","affiliation":[{"name":"Advanced Research Institute of Multidisciplinary Sciences, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4328-6339","authenticated-orcid":false,"given":"Kexin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1972-4194","authenticated-orcid":false,"given":"Haibo","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0275-8387","authenticated-orcid":false,"given":"Jinhu","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.paerosci.2021.100696"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2514\/3.19884"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2514\/6.2012-4470"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_17"},{"key":"ref5","first-page":"1587","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2021.3121809"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2020.106442"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2022.3141229"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3096997"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2021.3103503"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.xinn.2021.100162"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/GNCC42960.2018.9018872"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/app10186567"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.2514\/1.I010970"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2020.105746"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.actaastro.2020.01.007"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2018.2824679"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3056384"},{"key":"ref19","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref20","article-title":"Tsallis reinforcement learning: A unified framework for maximum entropy reinforcement learning","author":"Lee","year":"2019","journal-title":"arXiv:1902.00137"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2018.2871888"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref25","first-page":"5048","article-title":"Hindsight experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Andrychowicz"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.06.024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref28","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. 16th Int. Conf. Mach. Learn.","author":"Andrew"},{"key":"ref29","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref30","first-page":"1","article-title":"Prioritized experience replay","volume-title":"Proc. 4th Int. Conf. Learn. Represent.","author":"Schaul"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2015.06.003"}],"container-title":["IEEE Transactions on Circuits and Systems I: Regular Papers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8919\/9809931\/09782560.pdf?arnumber=9782560","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:01:15Z","timestamp":1706756475000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9782560\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":31,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsi.2022.3163463","relation":{},"ISSN":["1549-8328","1558-0806"],"issn-type":[{"value":"1549-8328","type":"print"},{"value":"1558-0806","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7]]}}}