{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T20:07:28Z","timestamp":1779826048521,"version":"3.53.1"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":["62473052"],"award-info":[{"award-number":["62473052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Laboratory","award":["241-HF-D09-01"],"award-info":[{"award-number":["241-HF-D09-01"]}]},{"DOI":"10.13039\/501100001809","name":"China Scholarship Council Program","doi-asserted-by":"publisher","award":["202506030077"],"award-info":[{"award-number":["202506030077"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2026,6,1]]},"DOI":"10.1109\/jiot.2026.3674392","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T20:16:26Z","timestamp":1773692186000},"page":"24893-24911","source":"Crossref","is-referenced-by-count":0,"title":["PRIME: Policy Representation Integration With Metavalue-Modulated Evolution in Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9309-5628","authenticated-orcid":false,"given":"Licheng","family":"Sun","sequence":"first","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5734-3157","authenticated-orcid":false,"given":"Hongbin","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3535148"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3614991"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3386888"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3545496"},{"key":"ref6","first-page":"10706","article-title":"Q-value path decomposition for deep multiagent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref7","first-page":"376","article-title":"Dealing with non-stationarity in decentralized cooperative multi-agent deep reinforcement learning via multi-timescale learning","volume-title":"Proc. Conf. Lifelong Learn. Agents","author":"Nekoei"},{"key":"ref8","first-page":"1188","article-title":"Evolution-guided policy gradient in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Khadka"},{"key":"ref9","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"Salimans","year":"2017","journal-title":"arXiv:1703.03864"},{"key":"ref10","first-page":"19490","article-title":"Race: Improve multi-agent reinforcement learning with representation asymmetry and collaborative evolution","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref11","first-page":"14398","article-title":"Model-free opponent shaping","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lu"},{"key":"ref12","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe"},{"key":"ref13","first-page":"13458","article-title":"Settling the variance of multi-agent policy gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Kuba"},{"key":"ref14","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv:1706.05296"},{"issue":"178","key":"ref15","first-page":"1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Son"},{"key":"ref17","first-page":"12208","article-title":"FACMAC: Factored multi-agent centralised policy gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Peng"},{"key":"ref18","first-page":"2701","article-title":"VAIN: Attentional multi-agent predictive modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Hoshen"},{"key":"ref19","article-title":"Graph convolutional reinforcement learning","author":"Jiang","year":"2018","journal-title":"arXiv:1810.09202"},{"key":"ref20","article-title":"Learning transferable cooperative behavior in multi-agent teams","author":"Agarwal","year":"2019","journal-title":"arXiv:1906.01202"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/604"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341405"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/evco.1993.1.1.1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3569096"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5728"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126628"},{"key":"ref27","article-title":"Learning with opponent-learning awareness","author":"Foerster","year":"2017","journal-title":"arXiv:1709.04326"},{"key":"ref28","first-page":"1529","article-title":"Dice: The infinitely differentiable Monte Carlo estimator","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Foerster"},{"key":"ref29","first-page":"5541","article-title":"A policy gradient algorithm for learning to learn in multiagent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref30","article-title":"Continuous adaptation via meta-learning in nonstationary and competitive environments","author":"Al-Shedivat","year":"2017","journal-title":"arXiv:1710.03641"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339515"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i9.21165"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.23860\/diss-li-hepfeng-2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/21M1467249"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11534158\/11434949.pdf?arnumber=11434949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T19:42:29Z","timestamp":1779824549000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434949\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,1]]},"references-count":34,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2026.3674392","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,1]]}}}