{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T12:08:39Z","timestamp":1768910919175,"version":"3.49.0"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"SmartSat CRC through Australian Government\u2019s CRC Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3652508","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:02:28Z","timestamp":1768255348000},"page":"6238-6260","source":"Crossref","is-referenced-by-count":0,"title":["Intelligent Spacecraft Attitude Fault Recovery Using Deep Reinforcement Learning"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1378-2235","authenticated-orcid":false,"given":"Ghaith","family":"El-Dalahmeh","sequence":"first","affiliation":[{"name":"Swinburne University of Technology, Hawthorn, Melbourne, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2631-1168","authenticated-orcid":false,"given":"Mohammad","family":"Reza Jabbarpour","sequence":"additional","affiliation":[{"name":"Swinburne University of Technology, Hawthorn, Melbourne, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7404-110X","authenticated-orcid":false,"given":"Bao","family":"Quoc Vo","sequence":"additional","affiliation":[{"name":"Swinburne University of Technology, Hawthorn, Melbourne, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0937-4028","authenticated-orcid":false,"given":"Ryszard","family":"Kowalczyk","sequence":"additional","affiliation":[{"name":"University of South Australia, Adelaide, Australia"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep learning fault protection applied to spacecraft attitude determination and control","author":"Mansell","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2514\/1.I010881"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.61173\/yt74cp68"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/machines12120856"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.asr.2023.02.025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/AERO63441.2025.11068576"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijcip.2022.100516"},{"key":"ref8","article-title":"A survey for deep reinforcement learning based network intrusion detection","author":"Yang","year":"2024","journal-title":"arXiv:2410.07612"},{"key":"ref9","article-title":"Reinforcement learning-based resilience and decision making in cyber-physical systems","author":"Sangoleye","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3477415"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1186\/s42400-021-00095-5"},{"key":"ref12","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref13","first-page":"5048","article-title":"Hindsight experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Andrychowicz"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3185424"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2514\/6.2023-1439"},{"key":"ref16","first-page":"1","article-title":"Reinforcement learning for spacecraft navigation & environment characterization in the planar-restricted two-body problem","volume-title":"Proc. AAS\/AIAA Spaceflight Mech. Meeting","author":"Getzandanner"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.36001\/phmconf.2020.v12i1.1272"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/I4CT.2014.6914151"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICoAC59537.2023.10249887"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JMASS.2024.3402984"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1093\/ijlct\/ctaa020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICECA.2019.8822165"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2011.2107719"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2023.3294170"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.actaastro.2013.12.003"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/0142331215611210"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.7603\/s40957-015-0009-7"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2020.106192"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.2514\/1.G003909"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-6670(17)52320-4"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/01423312221149410"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS48674.2020.9213890"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/RAST.2017.8002962"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1981.1102603"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-023-08620-6"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2023.08.001"},{"issue":"1","key":"ref37","first-page":"108","article-title":"Artificial intelligence for the real world","volume":"96","author":"Davenport","year":"2018","journal-title":"Harvard Bus. Rev."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref39","first-page":"272","article-title":"Satellite attitude acquisition using a neural network controller","author":"Carrara","year":"2000","journal-title":"Advances in Space Dynamics; Advances in Space Dynamics"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1090\/s0002-9904-1954-09848-8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref42","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref43","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref44","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref45","article-title":"Trust region policy optimization","author":"Schulman","year":"2015","journal-title":"arXiv:1502.05477"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/GNCC42960.2018.9018642"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.2514\/6.2020-1600"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.099"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2024.109522"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2024.1402846"},{"key":"ref51","article-title":"Attitude fault-tolerant control applied to microsatellite","author":"Henna","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.asr.2019.12.030"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/8874619"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s42401-022-00169-3"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2018.09.583"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3582523"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2023.04.019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2011.940459"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.2514\/6.2015-0596"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.2514\/1.A35294"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-0802-8_3"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.2514\/1.54254"},{"key":"ref63","volume-title":"Spacecraft Attitude Dynamics","author":"Hughes","year":"2012"},{"key":"ref64","article-title":"Robust microvibration control and worst-case analysis for high pointing stability space missions","author":"Preda","year":"2017"},{"key":"ref65","first-page":"420","article-title":"Adaptive continuous control of spacecraft attitude using deep reinforcement learning","volume-title":"Proc. AAS\/AIAA Astrodyn. Spec. Conf.","author":"Elkins"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.2514\/1.I010762"},{"key":"ref67","first-page":"1","article-title":"DHER: Hindsight experience replay for dynamic goals","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Fang"},{"key":"ref68","article-title":"Intrinsic exploration for reinforcement learning beyond rewards","author":"Creus-Castanyer","year":"2024"},{"issue":"181","key":"ref69","first-page":"1","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"Narvekar","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref70","article-title":"Gradient-norm constrained algorithm on offline and online learning","author":"Zhang","year":"2023","journal-title":"SSRN 4663051"},{"key":"ref71","article-title":"Addressing high-dimensional continuous action space via decomposed discrete policy-critic","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhang","year":"2022"},{"key":"ref72","first-page":"2586","article-title":"Dimension-wise importance sampling weight clipping for sample-efficient reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Han"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.2322\/tjsass.44.133"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-024-03733-1"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2023.102440"},{"key":"ref77","article-title":"MATA-RL: Continuous reaction wheel attitude control using the mata simulation software and reinforcement learning","volume-title":"Proc. Small Satell. Conf.","author":"Tan","year":"2021"},{"issue":"268","key":"ref78","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref79","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1177\/09544100251342544"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11343832.pdf?arnumber=11343832","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T20:55:40Z","timestamp":1768856140000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11343832\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3652508","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}