{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:31:57Z","timestamp":1775579517226,"version":"3.50.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3035152","type":"journal-article","created":{"date-parts":[[2020,11,2]],"date-time":"2020-11-02T16:13:24Z","timestamp":1604333604000},"page":"199254-199265","source":"Crossref","is-referenced-by-count":28,"title":["Double Deep-Q Learning-Based Output Tracking of Probabilistic Boolean Control Networks"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4349-6320","authenticated-orcid":false,"given":"Antonio","family":"Acernese","sequence":"first","affiliation":[{"name":"Department of Engineering, University of Sannio, Benevento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3994-3842","authenticated-orcid":false,"given":"Amol","family":"Yerudkar","sequence":"additional","affiliation":[{"name":"Department of Engineering, University of Sannio, Benevento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2753-1787","authenticated-orcid":false,"given":"Luigi","family":"Glielmo","sequence":"additional","affiliation":[{"name":"Department of Engineering, University of Sannio, Benevento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6937-9678","authenticated-orcid":false,"given":"Carmen Del","family":"Vecchio","sequence":"additional","affiliation":[{"name":"Department of Engineering, University of Sannio, Benevento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1049\/iet-syb:20070015"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6426443"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2020.2977417"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.12.087"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2019.8914068"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2016.02.035"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1088\/1478-3975\/9\/5\/055001"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymeth.2012.10.012"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2010.2043294"},{"key":"ref34","author":"cheng","year":"2011","journal-title":"Analysis and Control of Boolean Networks A Semi-Tensor Product Approach"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2910593"},{"key":"ref27","first-page":"223","article-title":"Sampled-data set stabilization of switched Boolean control networks","author":"yerudkar","year":"2020","journal-title":"Proc 21st IFAC World Congr (IFAC)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.108934"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.fss.2005.01.009"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2985302"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2851391"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2934740"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2828128"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2019.2925870"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3002533"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2018.8550347"},{"key":"ref50","first-page":"2613","article-title":"Double Q-learning","volume":"23","author":"van hasselt","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref55","first-page":"1","article-title":"Learning rates for Q-learning","volume":"1","author":"even-dar","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2968836"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3003552"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1089\/cmb.2011.0031"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500630"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2885530"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2013.6760515"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2018.02.010"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1007324"},{"key":"ref14","first-page":"1","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"2016","journal-title":"Proc 13th AAAI Conf Artif Intell"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/18.2.261"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2008.2003092"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2720730"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2294821"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2990489"},{"key":"ref4","first-page":"154","article-title":"A machine learning approach to classify pedestrians’ events based on imu and gps","volume":"17","author":"ahmed","year":"2019","journal-title":"Artific Intellig Int J"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.arcontrol.2018.09.005","article-title":"Reinforcement learning for control: Performance, stability, and deep approximators","volume":"46","author":"bu?oniu","year":"2018","journal-title":"Annu Rev Control"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejcon.2020.08.001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3182\/20070709-3-RO-4910.00004"},{"key":"ref8","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":"ref7","article-title":"Learning from delayed rewards","author":"watkins","year":"1989"},{"key":"ref49","first-page":"3014","article-title":"Weighted importance sampling for off-policy learning with linear function approximation","volume":"27","author":"mahmood","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISCID.2016.2054"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref45","volume":"5","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref48","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv 1511 05952"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref42","article-title":"Deep reinforcement learning for control of probabilistic Boolean networks","author":"papagiannis","year":"2019","journal-title":"arXiv 1909 03331"},{"key":"ref41","article-title":"Toggling a genetic switch using reinforcement learning","author":"sootla","year":"2013","journal-title":"arXiv 1303 3183"},{"key":"ref44","volume":"1","author":"bertsekas","year":"1995","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref43","first-page":"337","article-title":"Reinforcement learning approach to feedback stabilization problem of probabilistic Boolean control networks","volume":"5","author":"acernese","year":"2021","journal-title":"Syst Control Lett"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09246500.pdf?arnumber=9246500","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T06:00:07Z","timestamp":1769493607000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9246500\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3035152","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}