{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T21:19:07Z","timestamp":1772918347155,"version":"3.50.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"19","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2022,10,1]]},"DOI":"10.1109\/jiot.2022.3166110","type":"journal-article","created":{"date-parts":[[2022,4,14]],"date-time":"2022-04-14T15:38:55Z","timestamp":1649950735000},"page":"19260-19272","source":"Crossref","is-referenced-by-count":64,"title":["D3PG: Dirichlet DDPG for Task Partitioning and Offloading With Constrained Hybrid Action Space in Mobile-Edge Computing"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4070-5289","authenticated-orcid":false,"given":"Laha","family":"Ale","sequence":"first","affiliation":[{"name":"Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA"}]},{"given":"Scott A.","family":"King","sequence":"additional","affiliation":[{"name":"Department of Computing Sciences, Texas A&M University at Corpus Christi, Corpus Christi, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8781-4925","authenticated-orcid":false,"given":"Ning","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1598-4674","authenticated-orcid":false,"given":"Abdul Rahman","family":"Sattar","sequence":"additional","affiliation":[{"name":"Research and Development, Arctic Wolf Networks, Markham, ON, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4402-9468","authenticated-orcid":false,"given":"Janahan","family":"Skandaraniyam","sequence":"additional","affiliation":[{"name":"Research and Development, Arctic Wolf Networks, Markham, ON, Canada"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3035542"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3001597"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2019.2898657"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshps45667.2019.9024603"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.3003036"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2996784"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2017.8292514"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref9","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref11","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. 4th Int. Conf. Learn. Represent. (ICLR)","author":"Lillicrap"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2021.3066619"},{"key":"ref13","first-page":"1","article-title":"Deep reinforcement learning in parameterized action space","volume-title":"Proc. 4th Int. Conf. Learn. Represent. (ICLR)","author":"Hausknecht"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3041405"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2988386"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2922613"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC45663.2020.9120484"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2892508"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2869750"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2981338"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/OJVT.2020.2965100"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2934002"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2979523"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s41928-018-0059-3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2897005"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2903245"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2019.2903655"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2903191"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2906789"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3009540"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3006922"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3026589"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10226"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2017.33"},{"key":"ref36","article-title":"Parametrized deep Q-networks learning: Reinforcement learning with discrete-continuous hybrid action space","author":"Xiong","year":"2018","journal-title":"arXiv:1810.06394"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/323"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2019.8843223"},{"key":"ref39","article-title":"Continuous-discrete reinforcement learning for hybrid control in robotics","author":"Neunert","year":"2020","journal-title":"arXiv:2001.00449"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2016.2599530"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2018.2831230"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref44","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. 31st Int. Conf. Mach. Learn.","volume":"32","author":"Silver"},{"issue":"3","key":"ref45","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2649-2"},{"key":"ref47","first-page":"2587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","volume":"4","author":"Fujimoto"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2020.2971647"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/9899827\/09757749.pdf?arnumber=9757749","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T16:28:54Z","timestamp":1705940934000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9757749\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,1]]},"references-count":48,"journal-issue":{"issue":"19"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2022.3166110","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.17203607.v2","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.17203607.v1","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.17203607","asserted-by":"object"}]},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,1]]}}}