{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:37:00Z","timestamp":1774539420447,"version":"3.50.1"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004147","name":"Tsinghua University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018913","name":"Tsinghua Shenzhen International Graduate School","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018913","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1109\/vtc2022-fall57202.2022.10012942","type":"proceedings-article","created":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T18:52:20Z","timestamp":1674067940000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Heterogeneous Mean-Field Multi-Agent Reinforcement Learning for Communication Routing Selection in SAGI-Net"],"prefix":"10.1109","author":[{"given":"Hengxi","family":"Zhang","sequence":"first","affiliation":[{"name":"Tsinghua University,Tsinghua-Berkeley Shenzhen Institute,Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaze","family":"Tang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua-Berkeley Shenzhen Institute,Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanquan","family":"Hu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua-Berkeley Shenzhen Institute,Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoli","family":"Wei","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua-Berkeley Shenzhen Institute,Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenye","family":"Wu","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong,School of Science and Engineering,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbo","family":"Ding","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong,School of Science and Engineering,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao-Ping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua-Berkeley Shenzhen Institute,Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2015.2444095"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2841996"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933962"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3008299"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2016.2641959"},{"key":"ref6","article-title":"On the approximation of cooperative heterogeneous multi-agent reinforcement learning (marl) using mean field control (mfc)","author":"Mondal","year":"2021","journal-title":"arXiv preprint arXiv:2109.04024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.86.026116"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1090.0741"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3116593"},{"key":"ref10","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume-title":"in International conference on machine learning. PMLR","author":"Yang"},{"key":"ref11","article-title":"Multi type mean field reinforcement learning","author":"Subramanian","year":"2020","journal-title":"arXiv preprint arXiv:2002.02513"},{"key":"ref12","first-page":"39","volume-title":"WINNER II Channel Models","author":"D\u00f6ttling","year":"2010"},{"key":"ref13","volume-title":"3rd Generation Partnership Project; Technical Specification Group Radio Access Network;Study on Enhanced LTE Support for Aerial Vehicles: (Release 15), Standard 3GPP TR","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2014.2342736"},{"key":"ref15","volume-title":"3rd Generation Partnership Project; Technical Specification Group Radio Access Network; Study on New Radio (NR) to support non-terrestrial networks: (Release 15), Standard 3GPP TR","year":"2020"}],"event":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","location":"London, United Kingdom","start":{"date-parts":[[2022,9,26]]},"end":{"date-parts":[[2022,9,29]]}},"container-title":["2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10012685\/10012692\/10012942.pdf?arnumber=10012942","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T08:48:32Z","timestamp":1707468512000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10012942\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/vtc2022-fall57202.2022.10012942","relation":{},"subject":[],"published":{"date-parts":[[2022,9]]}}}