{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T18:23:27Z","timestamp":1775327007445,"version":"3.50.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20444"],"award-info":[{"award-number":["U21A20444"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62332019"],"award-info":[{"award-number":["62332019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2336214"],"award-info":[{"award-number":["U2336214"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFB3107603"],"award-info":[{"award-number":["2023YFB3107603"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/twc.2024.3392608","type":"journal-article","created":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T20:06:51Z","timestamp":1714507611000},"page":"12440-12454","source":"Crossref","is-referenced-by-count":6,"title":["Efficient Communications in Multi-Agent Reinforcement Learning for Mobile Applications"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3880-5069","authenticated-orcid":false,"given":"Zefang","family":"Lv","sequence":"first","affiliation":[{"name":"Department of Informatics and Communication Engineering and the Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2402-611X","authenticated-orcid":false,"given":"Liang","family":"Xiao","sequence":"additional","affiliation":[{"name":"Department of Informatics and Communication Engineering and the Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1480-4443","authenticated-orcid":false,"given":"Yousong","family":"Du","sequence":"additional","affiliation":[{"name":"Department of Informatics and Communication Engineering and the Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunjun","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Informatics and Communication Engineering and the Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9606-3476","authenticated-orcid":false,"given":"Shuai","family":"Han","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5774-1916","authenticated-orcid":false,"given":"Yong-Jin","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3036962"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3153316"},{"key":"ref3","first-page":"2145","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Foerster"},{"key":"ref4","first-page":"1538","article-title":"TarMAC: Targeted multi-agent communication","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Das"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3051163"},{"key":"ref6","first-page":"22069","article-title":"Learning individually inferred communication for multi-agent cooperation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Ding"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3220870"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3057826"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3188473"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3153175"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.3013599"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2933417"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3022705"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3229033"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3204794"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3104633"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3230711"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3268082"},{"key":"ref19","first-page":"2252","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Sukhbaatar"},{"key":"ref20","first-page":"15230","article-title":"Learning to ground multi-agent communication with autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Lin"},{"key":"ref21","first-page":"1538","article-title":"Communication in multi-agent reinforcement learning: Intention sharing","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kim"},{"key":"ref22","first-page":"2252","article-title":"Learning attentional communication for multi-agent cooperation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Jiang"},{"key":"ref23","first-page":"3235","article-title":"Efficient communication in multi-agent reinforcement learning via variance based control","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Zhang"},{"key":"ref24","first-page":"9908","article-title":"Learning efficient multi-agent communication: An information bottleneck approach","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3087248"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5957"},{"key":"ref27","first-page":"1","article-title":"ToM2C: Target-oriented multi-agent communication and cooperation with theory of mind","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM54140.2023.10436844"},{"key":"ref29","first-page":"2132","article-title":"Effects of task similarity on policy transfer with selective exploration in reinforcement learning","volume-title":"Proc. Int. Conf. Auto. Agents Multiagent Syst.","author":"Narayan"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3284611"},{"key":"ref31","first-page":"1","article-title":"Learning invariant representations for reinforcement learning without reconstruction","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref34","first-page":"1","article-title":"Is Q-learning provably efficient?","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Jin"},{"key":"ref35","volume-title":"Latitude Matrice 200 V2 Series Technical Parameters","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3149396"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2015.2492556"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2003.809401"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7693\/10678756\/10516313.pdf?arnumber=10516313","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T06:18:50Z","timestamp":1726121930000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10516313\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":38,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/twc.2024.3392608","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}