{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T04:42:19Z","timestamp":1781325739041,"version":"3.54.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Institute of Information & Communications Technology Planning & Evaluation (IITP) Information Technology Research Center (ITRC) Grant funded by the Korea Government","award":["IITP-2025-RS-2020-II201795"],"award-info":[{"award-number":["IITP-2025-RS-2020-II201795"]}]},{"name":"Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education","award":["RS-2024-00451716"],"award-info":[{"award-number":["RS-2024-00451716"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2025,6,1]]},"DOI":"10.1109\/jiot.2025.3534242","type":"journal-article","created":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T18:43:54Z","timestamp":1739472234000},"page":"16748-16760","source":"Crossref","is-referenced-by-count":2,"title":["MultiFedRL: Efficient Training of Service Agents for Heterogeneous Internet of Things Environments"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5887-5948","authenticated-orcid":false,"given":"KyeongDeok","family":"Baek","sequence":"first","affiliation":[{"name":"School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3843-263X","authenticated-orcid":false,"given":"In-Young","family":"Ko","sequence":"additional","affiliation":[{"name":"School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3353793"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2014.2306328"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2010.3"},{"key":"ref4","first-page":"8","article-title":"Towards the Web of things: Web mashups for embedded devices","volume-title":"Proc. Workshop Mashups, Enterprise Mashups Lightweight Compos. Web (MEM) (Int. World Wide Web Conf.)","author":"Guinard"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2914920.2929906"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3613279"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3276774.3276788"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174007"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46295-0_1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3464960"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583293"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.304"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583540"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583264"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICEIEC49280.2020.9152222"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3211270"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3327495"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3299262"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref20","article-title":"A survey of reinforcement learning from human feedback","author":"Kaufmann","year":"2024","journal-title":"arXiv:2312.14925"},{"key":"ref21","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119499"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-022-01046-x"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00309"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2022.3192506"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3015958"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583212"},{"key":"ref28","first-page":"17716","article-title":"Federated learning with partial model personalization","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Pillutla"},{"key":"ref29","first-page":"18","article-title":"Federated reinforcement learning with environment heterogeneity","volume-title":"Proc. 25th Int. Conf. Artif. Intell. Statist.","author":"Jin"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3160699"},{"key":"ref31","article-title":"Federated learning with personalization layers","author":"Arivazhagan","year":"2019","journal-title":"arXiv:1912.00818"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-023-09633-6"},{"key":"ref33","first-page":"1","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. 30th Adv. Neural Inf. Process. Syst.","author":"Foerster"},{"key":"ref34","first-page":"1","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. 30th Adv. Neural Inf. Process. Syst.","author":"Sukhbaatar"},{"key":"ref35","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Adv. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05864-5"},{"key":"ref37","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583347"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592517"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00985"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121546"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5957"},{"key":"ref45","first-page":"1","article-title":"Learning attentional communication for multi-agent cooperation","volume-title":"Proc. 32nd Adv. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref46","first-page":"1173","article-title":"Learning efficient diverse communication for cooperative heterogeneous teaming","volume-title":"Proc. 21st Int. Conf. Auton. Agents Multiagent Syst.","author":"Seraj"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00154"},{"key":"ref48","first-page":"1","article-title":"Modular networks: Learning to decompose neural computation","volume-title":"Proc. 32nd Adv. Neural Inf. Process. Syst.","author":"Kirsch"},{"key":"ref49","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref50","article-title":"Sample efficient actor-critic with experience replay","author":"Wang","year":"2017","journal-title":"arXiv:1611.01224"},{"key":"ref51","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref53","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2017","journal-title":"arXiv:1412.6980"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3466626"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.004"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11008454\/10886928.pdf?arnumber=10886928","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T17:41:01Z","timestamp":1747849261000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10886928\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,1]]},"references-count":55,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2025.3534242","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,1]]}}}