{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T10:21:30Z","timestamp":1779099690658,"version":"3.51.4"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100019779","name":"Qatar National Library","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100019779","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3551232","type":"journal-article","created":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T17:55:22Z","timestamp":1741974922000},"page":"49514-49526","source":"Crossref","is-referenced-by-count":2,"title":["Advanced Quantum Control With Ensemble Reinforcement Learning: A Case Study on the XY Spin Chain"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9634-3301","authenticated-orcid":false,"given":"Farshad","family":"Rahimi Ghashghaei","sequence":"first","affiliation":[{"name":"School of Computing and Digital Technology, Birmingham City University, Birmingham, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4267-8798","authenticated-orcid":false,"given":"Nebrase","family":"Elmrabit","sequence":"additional","affiliation":[{"name":"College of Computing and Information Technology, Ministry of Technical and Vocational Education, Zawia, Libya"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6552-7060","authenticated-orcid":false,"given":"Ayyaz-Ul-Haq","family":"Qureshi","sequence":"additional","affiliation":[{"name":"Department of Cyber Security and Networks, Glasgow Caledonian University, Glasgow, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8370-9290","authenticated-orcid":false,"given":"Adnan","family":"Akhunzada","sequence":"additional","affiliation":[{"name":"College of Computing and Information Technology, University of Doha for Science and Technology, Doha, Qatar"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0832-650X","authenticated-orcid":false,"given":"Mehdi","family":"Yousefi","sequence":"additional","affiliation":[{"name":"Independent Researcher, Glasgow, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1063\/5.0151346"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1557\/s43577-021-00133-0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1147\/jrd.2018.2888987"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/computers13070163"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.12.011059"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683463"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ad0100"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1117\/1.AP.5.1.016005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.8.031086"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1140\/epjqt\/s40507-022-00138-x"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s41745-022-00311-2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11467-022-1249-z"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2024.111987"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevApplied.15.014023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.926603"},{"issue":"6","key":"ref16","doi-asserted-by":"crossref","first-page":"2274","DOI":"10.1007\/s11424-023-2266-x","article-title":"Real-time optimal state estimation-based feedback control for stochastic quantum systems in the non-Markovian case","volume":"36","author":"Cong","year":"2023","journal-title":"J. Syst. Sci. Complex."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/s41534-019-0201-8"},{"key":"ref18","article-title":"Growing Q-networks: Solving continuous control tasks with adaptive control resolution","author":"Seyde","year":"2024","journal-title":"arXiv:2404.04253"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110975"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-4761-4_53"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1259"},{"issue":"4","key":"ref22","doi-asserted-by":"crossref","first-page":"458","DOI":"10.1080\/24725854.2023.2219281","article-title":"Decision-dependent distributionally robust Markov decision process method in dynamic epidemic control","volume":"56","author":"Song","year":"2023","journal-title":"IISE Trans."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.5.043002"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i9.28805"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.physleta.2022.128054"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1007\/978-981-15-4095-0_4","article-title":"Deep Q-networks","volume-title":"Deep Reinforcement Learning: Fundamentals, Research and Applications","author":"Huang","year":"2020"},{"key":"ref27","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/buildings12020131"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3054909"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3153502"},{"key":"ref31","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref32","article-title":"Revisiting design choices in proximal policy optimization","author":"Ching-Yun Hsu","year":"2020","journal-title":"arXiv:2009.10897"},{"key":"ref33","article-title":"You may not need ratio clipping in PPO","author":"Sun","year":"2022","journal-title":"arXiv:2202.00079"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20820"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.97.052333"},{"key":"ref36","volume-title":"Python","year":"2019"},{"key":"ref37","volume-title":"TensorFlow","year":"2019"},{"key":"ref38","volume-title":"SciPy.org\u2014SciPy.org","year":"2020"},{"key":"ref39","volume-title":"Matplotlib: Python Plotting\u2014Matplotlib 3.1.1 Documentation","year":"2012"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10926186.pdf?arnumber=10926186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T18:50:44Z","timestamp":1742842244000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10926186\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3551232","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}