{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T03:10:23Z","timestamp":1725073823169},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2019YFB1312001"]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Aerosp. Electron. Syst."],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1109\/taes.2022.3211246","type":"journal-article","created":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T20:31:37Z","timestamp":1664829097000},"page":"4902-4916","source":"Crossref","is-referenced-by-count":16,"title":["Space Noncooperative Object Active Tracking With Deep Reinforcement Learning"],"prefix":"10.1109","volume":"58","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-9106-9542","authenticated-orcid":false,"given":"Dong","family":"Zhou","sequence":"first","affiliation":[{"name":"Department of Control Science and Engineering, Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-1623-2220","authenticated-orcid":false,"given":"Guanghui","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-5438-4391","authenticated-orcid":false,"given":"Wenxiao","family":"Lei","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-8198-5267","authenticated-orcid":false,"given":"Ligang","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Harbin Institute of Technology, Harbin, China"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00276"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918770733"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"ref31","article-title":"Distributed distributional deterministic policy gradients","author":"barth-maron","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2514\/1.A34838"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2957464"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2899570"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2020.2988170"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.actaastro.2021.07.023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.actaastro.2017.11.006"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0954410019866282"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345390"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"key":"ref16","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2942989"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref28","first-page":"1","article-title":"Spacecraft decision-making autonomy using deep reinforcement learning","author":"harris","year":"0","journal-title":"Proceedings of the AAS\/AIAA Space Flight Mechanics Meeting"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2019.2934373"},{"key":"ref27","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.actaastro.2016.02.003"},{"key":"ref6","article-title":"3D visual tracking framework with deep learning for asteroid exploration","author":"zhou","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.2514\/6.2020-1600"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.2514\/6.2018-5353"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1117\/12.2247306"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2514\/1.A32813"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.paerosci.2014.03.002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.actaastro.2018.06.061"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2017.2671558"},{"key":"ref46","first-page":"7487","article-title":"Stabilizing transformers for reinforcement learning","author":"parisotto","year":"0","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref45","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","author":"janner","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2952590"},{"key":"ref21","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00359"},{"key":"ref24","article-title":"Prioritized experience replay","author":"schaul","year":"0","journal-title":"Proc Int Conf Learn Representations (Poster)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref23","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"0","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref44","article-title":"Transformer based reinforcement learning for games","author":"upadhyay","year":"2019"},{"key":"ref26","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref25","article-title":"Continuous Control With Deep Reinforcement Learning","author":"lillicrap","year":"0","journal-title":"Proc Int Conf Learn Representations (Poster)"}],"container-title":["IEEE Transactions on Aerospace and Electronic Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7\/9970423\/09907788.pdf?arnumber=9907788","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:21:47Z","timestamp":1672082507000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9907788\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":47,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/taes.2022.3211246","relation":{},"ISSN":["0018-9251","1557-9603","2371-9877"],"issn-type":[{"value":"0018-9251","type":"print"},{"value":"1557-9603","type":"electronic"},{"value":"2371-9877","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12]]}}}
