{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T17:26:50Z","timestamp":1781285210351,"version":"3.54.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"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"}]},{"name":"Industrial Research Chair Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Electron."],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1109\/tie.2021.3099234","type":"journal-article","created":{"date-parts":[[2021,7,28]],"date-time":"2021-07-28T19:53:02Z","timestamp":1627501982000},"page":"7491-7499","source":"Crossref","is-referenced-by-count":10,"title":["Reinforcement Learning With Constrained Uncertain Reward Function Through Particle Filtering"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6745-4117","authenticated-orcid":false,"given":"Oguzhan","family":"Dogru","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5546-0918","authenticated-orcid":false,"given":"Ranjith","family":"Chiplunkar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9082-2216","authenticated-orcid":false,"given":"Biao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1090\/s0002-9904-1954-09848-8"},{"key":"ref2","article-title":"Auto-encoding variational Bayes","author":"Kingma"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-32025-0_14"},{"key":"ref4","volume-title":"System Identification","author":"Ljung","year":"1999"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/9781118501054"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.3014574"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2020.3033943"},{"key":"ref8","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref9","author":"Bertsekas","year":"2019","journal-title":"Reinforcement Learning and Optimal Control"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref11","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2782205"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/pr5030046"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2020.106886"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2020.106939"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2020.104331"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.2988189"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.2992003"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2021.04.027"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109451"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109421"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2020.110080"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6086"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/656"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1002\/0470045345"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1021\/ie960583e"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1080\/00207720903042970"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MED.2008.4602001"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2014.02.013"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053011528"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2016.08.015"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1002\/aic.14390"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2009.11.002"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2019.05.019"},{"issue":"3\/4","key":"ref37","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1023\/A:1022676722315","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref39","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_20"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.11.032"},{"key":"ref42","article-title":"Kalman meets Bellman: Improving policy evaluation through value tracking","author":"Shashua","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2019.01.017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3182\/20080706-5-KR-1001.00560"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2019.05.011"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109184"},{"key":"ref47","article-title":"Discounted reinforcement learning is not an optimization problem","author":"Naik","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/BF00143942"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA.2005.195385"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206879"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/SIPS.2010.5624805"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s13398-014-0173-7.2"}],"container-title":["IEEE Transactions on Industrial Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/41\/9709233\/09499958.pdf?arnumber=9499958","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T22:45:51Z","timestamp":1705013151000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9499958\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":52,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tie.2021.3099234","relation":{},"ISSN":["0278-0046","1557-9948"],"issn-type":[{"value":"0278-0046","type":"print"},{"value":"1557-9948","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7]]}}}