{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T15:20:14Z","timestamp":1784906414429,"version":"3.55.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"16","license":[{"start":{"date-parts":[[2023,8,15]],"date-time":"2023-08-15T00:00:00Z","timestamp":1692057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,15]],"date-time":"2023-08-15T00:00:00Z","timestamp":1692057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,15]],"date-time":"2023-08-15T00:00:00Z","timestamp":1692057600000},"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":["62203257"],"award-info":[{"award-number":["62203257"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U19B2019"],"award-info":[{"award-number":["U19B2019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62104128"],"award-info":[{"award-number":["62104128"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["M-0248"],"award-info":[{"award-number":["M-0248"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004147","name":"Tsinghua University Initiative Scientific Research Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tsinghua-Meituan Joint Institute for Digital Life"},{"name":"Tsinghua-4paradigm Joint Research"},{"DOI":"10.13039\/501100017582","name":"Beijing National Research Center for Information Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100017582","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012282","name":"Beijing Innovation Center for Future Chips","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012282","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2023,8,15]]},"DOI":"10.1109\/jiot.2023.3240671","type":"journal-article","created":{"date-parts":[[2023,1,30]],"date-time":"2023-01-30T19:48:54Z","timestamp":1675108134000},"page":"14014-14027","source":"Crossref","is-referenced-by-count":25,"title":["Improving Sample Efficiency of Multiagent Reinforcement Learning With Nonexpert Policy for Flocking Control"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5069-6673","authenticated-orcid":false,"given":"Yunbo","family":"Qiu","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Jin","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4566-3820","authenticated-orcid":false,"given":"Lebin","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7683-6937","authenticated-orcid":false,"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6108-5157","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6465-7437","authenticated-orcid":false,"given":"Xudong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"401","article-title":"Flocking of multi-agents in constrained environments","volume":"2","author":"sharma","year":"2009","journal-title":"Eur J Pure Appl Math"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.2514\/1.G004227"},{"key":"ref34","first-page":"7472","article-title":"Multi-agent generative adversarial imitation learning","author":"song","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.3308"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2010.06.014"},{"key":"ref36","first-page":"465","article-title":"Integrating behavior cloning and reinforcement learning for improved performance in dense and sparse reward environments","author":"goecks","year":"2020","journal-title":"Proc 19th Int Conf Auton Agents MultiAgent Syst"},{"key":"ref31","first-page":"4572","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref30","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"ziebart","year":"2008","journal-title":"Proc AAAI"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICUS48101.2019.8995944"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2010.65"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2001.980728"},{"key":"ref32","first-page":"1995","article-title":"Coordinated multi-agent imitation learning","author":"le","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2022-Fall57202.2022.10012835"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SMC53654.2022.9945272"},{"key":"ref17","first-page":"6993","article-title":"Bipartite flock control of multi-agent systems","author":"fan","year":"2013","journal-title":"Proc IEEE 32nd Chin Control Conf"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1357\/1\/012026"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3046695"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3011211"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2015.2418871"},{"key":"ref18","first-page":"6947","article-title":"Flocking with a virtual leader based on distributed event-triggered hybrid control","author":"yu","year":"2013","journal-title":"Proc IEEE 32nd Chin Control Conf"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2018.8646428"},{"key":"ref46","first-page":"1","article-title":"Reducing overestimation bias in multi-agent domains using double centralized critics","author":"ackermann","year":"2019","journal-title":"Proc NeurIPS Workshop Deep RL"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981429"},{"key":"ref45","first-page":"1","article-title":"Diluted near-optimal expert demonstrations for guiding dialogue stochastic policy optimisation","author":"cordier","year":"2020","journal-title":"Proc NeurIPS Workshop Human Loop Dialogue Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA.2018.8444355"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103594"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2944892"},{"key":"ref42","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref41","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636183"},{"key":"ref44","first-page":"1530","article-title":"Obstacle avoidance for mobile robots using artificial potential field approach with simulated annealing","volume":"3","author":"park","year":"2001","journal-title":"Proc IEEE Int Symp Ind Electron Proc (ISIE)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3094207"},{"key":"ref43","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume":"34","author":"fujimoto","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/s20164546"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3016951"},{"key":"ref29","first-page":"305","article-title":"ALVINN: An autonomous land vehicle in a neural network","author":"pomerleau","year":"1988","journal-title":"Proc 1st Int Conf Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2981092"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3031622"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/37401.37406"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SAHCNW.2009.5172925"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-65283-2_24"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2979691"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.01.151"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.apor.2021.102759"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/10210448\/10029340.pdf?arnumber=10029340","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T18:04:12Z","timestamp":1693245852000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10029340\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,15]]},"references-count":46,"journal-issue":{"issue":"16"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2023.3240671","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,15]]}}}