{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:19:59Z","timestamp":1780762799052,"version":"3.54.1"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,2,15]],"date-time":"2025-02-15T00:00:00Z","timestamp":1739577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,15]],"date-time":"2025-02-15T00:00:00Z","timestamp":1739577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,15]],"date-time":"2025-02-15T00:00:00Z","timestamp":1739577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2025,2,15]]},"DOI":"10.1109\/jiot.2024.3481257","type":"journal-article","created":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T18:05:21Z","timestamp":1729101921000},"page":"3929-3947","source":"Crossref","is-referenced-by-count":3,"title":["Communication-Efficient Soft Actor\u2013Critic Policy Collaboration via Regulated Segment Mixture"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1098-7589","authenticated-orcid":false,"given":"Xiaoxue","family":"Yu","sequence":"first","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4297-5060","authenticated-orcid":false,"given":"Rongpeng","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengchao","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5479-7890","authenticated-orcid":false,"given":"Zhifeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM54140.2023.10437274"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103489"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.3012947"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3160697"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3172168"},{"key":"ref9","first-page":"6382","article-title":"Multi-agent actor\u2013critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref10","first-page":"1","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref12","first-page":"2145","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Foerster"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.20517\/ir.2021.02"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3279268"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3242734"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3219644"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3336670"},{"key":"ref18","first-page":"1","article-title":"Scalable evaluation of multi-agent reinforcement learning with melting pot","volume-title":"Proc. ICML","author":"Leibo"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3149860"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3332675"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/CNSM59352.2023.10327827"},{"key":"ref22","volume-title":"Melting pot: An evaluation suite for multi-agent reinforcement learning.","author":"Joel","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2964162"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/PerComWorkshops59983.2024.10503481"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM48099.2022.10001364"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3368025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3354507"},{"key":"ref29","first-page":"9709","article-title":"Cooperative SGD: A unified framework for the design and analysis of local-update SGD algorithms","volume":"22","author":"Wang","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSIPN.2022.3151242"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3196503"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2987550.2987586"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3251571"},{"key":"ref34","article-title":"Decentralized federated learning: A segmented gossip approach","author":"Hu","year":"2019","journal-title":"arXiv:1908.07782"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1561\/9781680837896"},{"key":"ref36","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. ICML","author":"Haarnoja"},{"key":"ref37","first-page":"1","article-title":"Soft actor\u2013critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. ICML","author":"Haarnoja"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2022.3144451"},{"key":"ref40","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proc. ICML","author":"Kakade"},{"key":"ref41","first-page":"1","article-title":"Trust region policy optimization in multi-agent reinforcement learning","volume-title":"Proc. ICLR","author":"Kuba"},{"key":"ref42","first-page":"1","article-title":"Trust region policy optimization","volume-title":"Proc. ICML","author":"Schulman"},{"key":"ref43","first-page":"1","article-title":"Distributed value functions","volume-title":"Proc. ICML","author":"Schneider"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2000.898377"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2702388"},{"key":"ref46","article-title":"Convergence theory of generalized distributed subgradient method with random quantization","author":"Xia","year":"2022","journal-title":"arXiv:2207.10969"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118400"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref50","article-title":"Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks","author":"Papoudakis","year":"2020","journal-title":"arXiv:2006.07869"},{"key":"ref51","volume-title":"OpenAI baselines.","author":"Dhariwal","year":"2017"},{"key":"ref52","article-title":"Is independent learning all you need in the starcraft multi-agent challenge?","author":"de Witt","year":"2020","journal-title":"arXiv:2011.09533"},{"key":"ref53","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-05816-6_3","volume-title":"Distributed Reinforcement Learning for Multi-Robot Decentralized Collective Construction","author":"Sartoretti","year":"2019"},{"key":"ref54","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. ICML","author":"Mnih"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3056418"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2955035"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2023.3250705"},{"key":"ref58","first-page":"1","article-title":"FedPAQ: A communication-efficient federated learning method with periodic averaging and quantization","volume-title":"Proc. AISTATS","author":"Reisizadeh"},{"key":"ref59","first-page":"1","article-title":"Communication compression for decentralized training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tang"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3230938"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3323433"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref63","first-page":"1","article-title":"Addressing function approximation error in actor\u2013critic methods","volume-title":"Proc. ICML","author":"Fujimoto"},{"issue":"1","key":"ref64","first-page":"4431","article-title":"On the theory of policy gradient methods: Optimality, approximation, and distribution shift","volume":"22","author":"Agarwal","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3390\/e21050485"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-22496-7_5"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.vehcom.2021.100396"},{"key":"ref68","first-page":"1","article-title":"A natural policy gradient","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kakade"},{"key":"ref69","volume-title":"Vehicular communications; basic set of applications; analysis of the collective perception service (CPS); (Release 2), Version 2.1.1","year":"2021"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017746"},{"key":"ref71","first-page":"9573","article-title":"Fast approximate natural gradient descent in a Kronecker factored eigenbasis","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"George"},{"key":"ref72","first-page":"735","article-title":"Deep learning via Hessian-free optimization","volume-title":"Proc. ICML","author":"Martens"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3087314"},{"key":"ref74","first-page":"399","article-title":"Benchmarks for reinforcement learning in mixed-autonomy traffic","volume-title":"Proc. 2nd Conf. Robot Learn.","author":"Vinitsky"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.2023.3249101"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2920738"},{"key":"ref78","volume-title":"Service requirements for enhanced V2X scenarios, (Release 18), Version 18.0.1","year":"2024"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2023-Spring57618.2023.10199985"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/10874850\/10720116.pdf?arnumber=10720116","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T06:01:34Z","timestamp":1738821694000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10720116\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,15]]},"references-count":79,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2024.3481257","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,15]]}}}