{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:39:22Z","timestamp":1781797162998,"version":"3.54.5"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2017YFE0125300"],"award-info":[{"award-number":["2017YFE0125300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Joint Fund","award":["U1801264"],"award-info":[{"award-number":["U1801264"]}]},{"DOI":"10.13039\/501100013058","name":"Jiangsu Provincial Key Research and Development Program","doi-asserted-by":"publisher","award":["BE2019648"],"award-info":[{"award-number":["BE2019648"]}],"id":[{"id":"10.13039\/501100013058","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw. Sci. Eng."],"published-print":{"date-parts":[[2023,9,1]]},"DOI":"10.1109\/tnse.2022.3167949","type":"journal-article","created":{"date-parts":[[2022,4,19]],"date-time":"2022-04-19T19:36:42Z","timestamp":1650397002000},"page":"2991-3006","source":"Crossref","is-referenced-by-count":53,"title":["Deep Reinforcement Learning Based Cooperative Partial Task Offloading and Resource Allocation for IIoT Applications"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5563-7688","authenticated-orcid":false,"given":"Fan","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Internet of Things Engineering, Hohai University, Changzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6921-7369","authenticated-orcid":false,"given":"Guangjie","family":"Han","sequence":"additional","affiliation":[{"name":"College of Internet of Things Engineering, Hohai University, Changzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0730-9230","authenticated-orcid":false,"given":"Li","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Internet of Things Engineering, Hohai University, Changzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2984-3231","authenticated-orcid":false,"given":"Miguel","family":"Mart\u00ednez-Garc\u00eda","sequence":"additional","affiliation":[{"name":"Department of Aeronautical and Automotive Engineering, Loughborough University, Loughborough, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1312-9527","authenticated-orcid":false,"given":"Yan","family":"Peng","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Institute, Shanghai University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2913162"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2999063"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2987567"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2971323"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.3018159"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2797187"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2790421"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2968951"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2972061"},{"key":"ref30","first-page":"1","article-title":"Prioritized experience replay","author":"schaul","year":"0","journal-title":"Proc 4th Int Conf Learn Representations"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2991773"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2882783"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3004500"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2993071"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.3009103"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2959035"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3123406"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2970110"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2878435"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3076795"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900406"},{"key":"ref46","first-page":"1","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"dan","year":"0","journal-title":"Proc 5th Int Conf Learn Representations"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2018.10.003"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2921159"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2959182"},{"key":"ref48","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3013990"},{"key":"ref47","first-page":"1846","article-title":"Latent space policies for hierarchical reinforcement learning","author":"haarnoja","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2021.3116251"},{"key":"ref42","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2868616"},{"key":"ref41","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"Proc 4th Int Conf Learn Representations"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3068427"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2019.1800386"},{"key":"ref43","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","author":"haarnoja","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref21","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":"ref28","first-page":"449","article-title":"A distributional perspective on reinforcement learning","author":"bellemare","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3016320"},{"key":"ref29","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-015-1133-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2016.2565621"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2750180"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.03.009"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"5118","DOI":"10.1109\/TII.2020.3007644","article-title":"Adaptive DE algorithm for novel energy control framework based on edge computing in IIoT applications","volume":"17","author":"han","year":"2021","journal-title":"IEEE Trans Ind Informat"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3096970"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2933238"},{"key":"ref40","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"0","journal-title":"Proc 33rd Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Network Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488902\/10256239\/09760005.pdf?arnumber=9760005","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T19:20:46Z","timestamp":1696879246000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9760005\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,1]]},"references-count":48,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnse.2022.3167949","relation":{},"ISSN":["2327-4697","2334-329X"],"issn-type":[{"value":"2327-4697","type":"electronic"},{"value":"2334-329X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,1]]}}}