{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T04:37:43Z","timestamp":1780807063002,"version":"3.54.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2019YFB2101704"],"award-info":[{"award-number":["2019YFB2101704"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202238"],"award-info":[{"award-number":["62202238"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20200752"],"award-info":[{"award-number":["BK20200752"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw. Serv. Manage."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tnsm.2023.3316626","type":"journal-article","created":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T17:56:39Z","timestamp":1695059799000},"page":"939-952","source":"Crossref","is-referenced-by-count":7,"title":["Offline Reinforcement Learning for Asynchronous Task Offloading in Mobile Edge Computing"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9406-4499","authenticated-orcid":false,"given":"Bolei","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1815-2793","authenticated-orcid":false,"given":"Fu","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Computer, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lifa","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref2","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. ICLR","author":"Lillicrap"},{"key":"ref3","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref4","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1186\/s13638-020-01801-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155373"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2019.2902661"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2867191"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref10","article-title":"AI2-THOR: An interactive 3D environment for visual AI","author":"Kolve","year":"2017","journal-title":"arXiv:1712.05474"},{"key":"ref11","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2015.2487344"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3035044"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2022.3188997"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/glocom.2013.6831252"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icc.2014.6883509"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/icc.2016.7511148"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3133586"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3073113"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3059692"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2016.2599530"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2013.6566921"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2022.3158000"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3175218"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/infocom.2019.8737560"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3091142"},{"key":"ref27","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Conf. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref29","first-page":"4292","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref30","first-page":"7611","article-title":"MAVEN: Multi-agent variational exploration","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Mahajan"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2935450"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6226"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313433"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3087258"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3096673"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2020.3048075"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00557-3_4"},{"key":"ref38","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref39","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref40","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230597"},{"key":"ref42","first-page":"14129","article-title":"MOPO: Model-based offline policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yu"},{"key":"ref43","first-page":"28954","article-title":"Combo: Conservative offline model-based policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yu"},{"key":"ref44","first-page":"10299","article-title":"Believe what you see: Implicit constraint approach for offline multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yang"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3233\/faia230390"},{"key":"ref46","volume-title":"Phase Transitions and Critical Phenomena","author":"Stanley","year":"1971"},{"key":"ref47","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton"}],"container-title":["IEEE Transactions on Network and Service Management"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4275028\/10423826\/10254572.pdf?arnumber=10254572","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,12]],"date-time":"2024-02-12T19:16:09Z","timestamp":1707765369000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10254572\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":47,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnsm.2023.3316626","relation":{},"ISSN":["1932-4537","2373-7379"],"issn-type":[{"value":"1932-4537","type":"electronic"},{"value":"2373-7379","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}