{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T19:03:03Z","timestamp":1762455783930,"version":"build-2065373602"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"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":["62373342"],"award-info":[{"award-number":["62373342"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Australian Research Council\u2019s Future Fellowship Funding Scheme","doi-asserted-by":"publisher","award":["FT220100656"],"award-info":[{"award-number":["FT220100656"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tcyb.2024.3521300","type":"journal-article","created":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T14:42:36Z","timestamp":1736260956000},"page":"712-725","source":"Crossref","is-referenced-by-count":4,"title":["Auxiliary Task-Based Deep Reinforcement Learning for Quantum Control"],"prefix":"10.1109","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3080-8238","authenticated-orcid":false,"given":"Shumin","family":"Zhou","sequence":"first","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5039-9916","authenticated-orcid":false,"given":"Hailan","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4847-565X","authenticated-orcid":false,"given":"Sen","family":"Kuang","sequence":"additional","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7425-3559","authenticated-orcid":false,"given":"Daoyi","family":"Dong","sequence":"additional","affiliation":[{"name":"CIICADA Lab, School of Engineering, Australian National University, Canberra, ACT, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2024.3476339"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3131252"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms9498"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05782-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20245-2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.129.050507"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.02.003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2921424"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109327"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3090676"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3358905"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2009.0508"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06004-9"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3324601"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2283574"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041469"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.22331\/q-2022-09-08-797"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3243187"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.12.011059"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-42901-3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s42005-019-0169-x"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1209\/0295-5075\/126\/60002"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41534-019-0198-z"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3117790"},{"key":"ref25","article-title":"Quantum reinforcement learning in continuous action space","author":"Wu","year":"2023","journal-title":"arXiv:2012.10711"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1126\/science.add4679"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.127.110502"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3153502"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.abn5130"},{"key":"ref30","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. 16th Int. Conf. Mach. Learn. (ICML),","author":"Ng"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-52255-7_33"},{"key":"ref32","article-title":"Learning to navigate in complex environments","author":"Mirowski","year":"2016","journal-title":"arXiv:1611.03673"},{"key":"ref33","first-page":"1","article-title":"Learning to navigate in cities without a map","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Mirowski"},{"key":"ref34","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"Jaderberg","year":"2016","journal-title":"arXiv:1611.05397"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6424"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3053414"},{"key":"ref39","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. 31st Int. Conf. Mach. Learn. (ICML)","volume":"32","author":"Silver"},{"key":"ref40","first-page":"1","article-title":"Actor-critic algorithms","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","volume":"12","author":"Konda"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2939174"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.46.6856"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814881"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6633\/ab1ca4"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.2200153"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/nphys2170"},{"key":"ref47","first-page":"1","article-title":"Hindsight experience replay","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","volume":"30","author":"Andrychowicz"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.68.1500"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1038\/s41534-019-0201-8"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2616384"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1515\/itms-2017-0003"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3140724"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11424-011-9066-4"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.105.022441"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.129.150501"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221036\/10870045\/10830787.pdf?arnumber=10830787","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:54:03Z","timestamp":1762455243000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10830787\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":55,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2024.3521300","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"type":"print","value":"2168-2267"},{"type":"electronic","value":"2168-2275"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}