{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T18:59:41Z","timestamp":1763665181230,"version":"3.45.0"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"23","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2021"],"award-info":[{"award-number":["U23B2021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Aircraft Swarm Intelligent Sensing and Cooperative Control Key Laboratory of Sichuan province"},{"DOI":"10.13039\/501100001809","name":"Sichuan Provincial Engineering Research Center of Communication Technology for Intelligent IoT","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2025,12,1]]},"DOI":"10.1109\/jiot.2025.3607864","type":"journal-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T17:33:29Z","timestamp":1757439209000},"page":"49248-49259","source":"Crossref","is-referenced-by-count":0,"title":["An Offline Learning Framework for Edge Resource Allocation and Task Offloading in Agricultural IoT With Limited Trajectory Data"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4294-3605","authenticated-orcid":false,"given":"Runhui","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Aeronautics and Astronautics, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1186-2373","authenticated-orcid":false,"given":"Wenjing","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Aeronautics and Astronautics, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0073-6101","authenticated-orcid":false,"given":"Hong","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Aeronautics and Astronautics, University of Electronic Science and Technology of China, Chengdu, China"}]},{"given":"Dibao","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Aeronautics and Astronautics, University of Electronic Science and Technology of China, Chengdu, China"}]},{"given":"Yingwei","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Aeronautics and Astronautics, University of Electronic Science and Technology of China, Chengdu, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1003925"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3003910"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3013005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3199921"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1186\/s13677-024-00626-8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3150432"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3234706"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3338602"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2020.2996764"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3117511"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.2994232"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3064314"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2875246"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2928811"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3452502"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3196544"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN49398.2020.9209593"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3259394"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/BMSB62888.2024.10608276"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3227027"},{"key":"ref21","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref22","first-page":"7766","article-title":"The state of sparse training in deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Graesser"},{"key":"ref23","first-page":"20132","article-title":"A minimal approach to offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fujimoto"},{"key":"ref24","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":"ref25","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref26","first-page":"23851","article-title":"RORL: Robust offline reinforcement learning via conservative smoothing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yang"},{"key":"ref27","first-page":"1","article-title":"Diffusion policies as an expressive policy class for offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tnse.2025.3590545"},{"key":"ref29","first-page":"46323","article-title":"Synthetic experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Lu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3584698"},{"key":"ref31","first-page":"1","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11261327\/11153912.pdf?arnumber=11153912","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T18:44:04Z","timestamp":1763664244000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11153912\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":31,"journal-issue":{"issue":"23"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2025.3607864","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"type":"electronic","value":"2327-4662"},{"type":"electronic","value":"2372-2541"}],"subject":[],"published":{"date-parts":[[2025,12,1]]}}}