{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T11:41:29Z","timestamp":1774352489011,"version":"3.50.1"},"reference-count":20,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"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":["62276028"],"award-info":[{"award-number":["62276028"]}],"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":["U20A20167"],"award-info":[{"award-number":["U20A20167"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003787","name":"Natural Science Foundation of Hebei Province","doi-asserted-by":"publisher","award":["F202103079"],"award-info":[{"award-number":["F202103079"]}],"id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hebei Province Central Leading Local Science and Technology Development","award":["236Z1811G"],"award-info":[{"award-number":["236Z1811G"]}]},{"name":"Innovation Capability Improvement Plan Project of Hebei Province","award":["22567626H"],"award-info":[{"award-number":["22567626H"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/lra.2024.3389813","type":"journal-article","created":{"date-parts":[[2024,4,16]],"date-time":"2024-04-16T17:29:20Z","timestamp":1713288560000},"page":"5385-5392","source":"Crossref","is-referenced-by-count":5,"title":["MARRGM: Learning Framework for Multi-Agent Reinforcement Learning via Reinforcement Recommendation and Group Modification"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1228-2757","authenticated-orcid":false,"given":"Peiliang","family":"Wu","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Yanshan University, Qinhuangdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8053-7859","authenticated-orcid":false,"given":"Liqiang","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Yanshan University, Qinhuangdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2867-7512","authenticated-orcid":false,"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of software, Nankai University, TianJin, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6547-5150","authenticated-orcid":false,"given":"Bingyi","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Yanshan University, Qinhuangdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7683-2776","authenticated-orcid":false,"given":"Wenbai","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Information Science and Technology University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.10.014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3229236"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2023.102644"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3318552"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3329785"},{"key":"ref7","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe","year":"2017"},{"key":"ref8","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Iqbal","year":"2019"},{"key":"ref9","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2021"},{"key":"ref10","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","year":"2019"},{"key":"ref11","first-page":"1","article-title":"RODE: Learning roles to decompose multi-agent tasks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2021"},{"key":"ref12","first-page":"6826","article-title":"Cooperative exploration for multi-agent deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109436"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-023-09633-6"},{"key":"ref15","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Foerster","year":"2017"},{"key":"ref16","first-page":"5048","article-title":"Hindsight experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Andrychowicz","year":"2017"},{"key":"ref17","first-page":"443","article-title":"Lenient multi-agent deep reinforcement learning","volume-title":"Proc. 17th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Palmer","year":"2018"},{"key":"ref18","first-page":"3061","article-title":"Revisiting fundamentals of experience replay","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fedus","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108875"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462978"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10504377\/10502122.pdf?arnumber=10502122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T19:03:27Z","timestamp":1714763007000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10502122\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":20,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3389813","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}