{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T22:22:45Z","timestamp":1783722165297,"version":"3.55.0"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IIEEE Trans. Software Eng."],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1109\/tse.2023.3269804","type":"journal-article","created":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T18:33:04Z","timestamp":1682447584000},"page":"3715-3735","source":"Crossref","is-referenced-by-count":48,"title":["A Search-Based Testing Approach for Deep Reinforcement Learning Agents"],"prefix":"10.1109","volume":"49","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2411-7938","authenticated-orcid":false,"given":"Amirhossein","family":"Zolfagharian","sequence":"first","affiliation":[{"name":"School of Electrical Engineering and Computer Science (EECS), University of Ottawa, Ottawa, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8647-1676","authenticated-orcid":false,"given":"Manel","family":"Abdellatif","sequence":"additional","affiliation":[{"name":"Software and Information Technology Engineering Department, École de Technologie Supérieure, Montreal, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1393-1010","authenticated-orcid":false,"given":"Lionel C.","family":"Briand","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science (EECS), University of Ottawa, Ottawa, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0253-671X","authenticated-orcid":false,"given":"Mojtaba","family":"Bagherzadeh","sequence":"additional","affiliation":[{"name":"Cisco, Ottawa, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8501-7447","authenticated-orcid":false,"given":"Ramesh","family":"S","sequence":"additional","affiliation":[{"name":"Department of Research and Development, General Motors, Warren, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-8285-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-2233-5_10"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3387940.3391462"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2020.110767"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tse.2023.3243522"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180220"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10515-021-00313-x"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3293882.3330579"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3111139"},{"key":"ref14","article-title":"Adversarial attacks on neural network policies","author":"Huang","year":"2017"},{"key":"ref15","article-title":"Improving robustness of reinforcement learning for power system control with adversarial training","author":"Pan","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147846"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE52982.2021.00041"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/525"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.1482"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594201"},{"key":"ref21","first-page":"10","article-title":"State abstractions for lifelong reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Abel","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref24","article-title":"Notes on state abstractions","author":"Jiang","year":"2018"},{"issue":"5","key":"ref25","first-page":"1","article-title":"Towards a unified theory of state abstraction for MDPs","volume":"4","author":"Li","year":"2006","journal-title":"Proc. Int. Symp. Artif. Intell. Math."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238172"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-Companion.2019.00051"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238172"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238202"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5220\/0009821603140323"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409739"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref34","first-page":"21024","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref36","first-page":"11 225","article-title":"Adaptive reward-poisoning attacks against reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2020"},{"key":"ref37","article-title":"Reward poisoning in reinforcement learning: Attacks against unknown learners in unknown environments","author":"Rakhsha","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2022.07.602"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CCECE.2010.5575262"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/BF00175354"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICEC.1995.489161"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICST.2015.7102604"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/525"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1023\/a:1010933404324"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.2307\/2699986"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/evco.1996.4.2.113"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3361566"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-016-2474-6"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/WDDC.2007.4339452"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2751071"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCI.2017.8125811"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-014-1624-6"},{"key":"ref55","first-page":"2040","article-title":"Robust deep reinforcement learning with adversarial attacks","volume-title":"Proc. 17th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Pattanaik"},{"key":"ref56","article-title":"Stable baselines","author":"Hill","year":"2018"},{"key":"ref57","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref58","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2016"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2017.7989186"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1002\/9780470479216.corpsy0524"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1561\/9781601986290"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59762-7_11"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-46033-0_3"},{"key":"ref65","article-title":"Adversarial exploitation of policy imitation","author":"Behzadan","year":"2019"},{"key":"ref66","article-title":"Sequential triggers for watermarking of deep reinforcement learning policies","author":"Behzadan","year":"2019"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3433210.3453090"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/72"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1137\/0201010"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238202"},{"key":"ref71","volume-title":"Andrew G Barto Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.17"},{"key":"ref73","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref74","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref76","article-title":"L2rpn: Learning to run a power network in a sustainable world neurips2020 challenge design","author":"Marot","year":"2020"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/PowerTech46648.2021.9494982"},{"key":"ref78","first-page":"1","article-title":"Delving into adversarial attacks on deep policies","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Kos","year":"2017"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3450267.3450537"},{"key":"ref80","article-title":"Robust reinforcement learning using adversarial populations","author":"Vinitsky","year":"2020"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.23919\/acc45564.2020.9147846"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99229-7_34"},{"key":"ref83","article-title":"Whatever does not kill deep reinforcement learning, makes it stronger","author":"Behzadan","year":"2017"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01554-1_9"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3460319.3464802"}],"container-title":["IEEE Transactions on Software Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/32\/10185148\/10107813.pdf?arnumber=10107813","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T03:30:40Z","timestamp":1709263840000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10107813\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":83,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tse.2023.3269804","relation":{},"ISSN":["0098-5589","1939-3520","2326-3881"],"issn-type":[{"value":"0098-5589","type":"print"},{"value":"1939-3520","type":"electronic"},{"value":"2326-3881","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7]]}}}