{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T05:55:13Z","timestamp":1771480513647,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"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":["62233005"],"award-info":[{"award-number":["62233005"]}],"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":["U2441245"],"award-info":[{"award-number":["U2441245"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Global STEM Professorship and JC STEM Lab of Future Energy Systems"},{"name":"National Key Laboratory of Space Intelligent Control","award":["HTKJ2024KL502004"],"award-info":[{"award-number":["HTKJ2024KL502004"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M750904"],"award-info":[{"award-number":["2024M750904"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tcds.2025.3574031","type":"journal-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T13:25:58Z","timestamp":1748352358000},"page":"1536-1547","source":"Crossref","is-referenced-by-count":1,"title":["GoMIC: Enhancing Efficient Collaboration in Multiagent Reinforcement Learning Through Group-Specific Mutual Information"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3268-7788","authenticated-orcid":false,"given":"Jichao","family":"Wang","sequence":"first","affiliation":[{"name":"Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1473-5880","authenticated-orcid":false,"given":"Yi","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8914-8934","authenticated-orcid":false,"given":"Yichun","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1960-3456","authenticated-orcid":false,"given":"Shuai","family":"Mao","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Nantong University, Nantong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9659-0858","authenticated-orcid":false,"given":"Zhaoyang","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, City University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2750-8029","authenticated-orcid":false,"given":"Yang","family":"Tang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3323572"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2024.3368055"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3323987"},{"issue":"3","key":"ref4","first-page":"540","article-title":"Multi-agent reinforcement learning based game: A survey","volume":"51","author":"Li","year":"2025","journal-title":"Acta Autom. Sin."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i9.21171"},{"key":"ref6","article-title":"Action semantics network: Considering the effects of actions in multiagent systems","volume-title":"Proc. ICLR","author":"Wang","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v26i1.8380"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313433"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3362475"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2023.113856"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3124913"},{"key":"ref12","first-page":"1","article-title":"Multi-agent interactions modeling with correlated policies","volume-title":"Proc. ICLR","author":"Liu","year":"2020"},{"key":"ref13","first-page":"1","article-title":"Probabilistic recursive reasoning for multi-agent reinforcement learning","volume-title":"Proc. ICLR","author":"Wen","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-020-9967-6"},{"key":"ref15","first-page":"4292","article-title":"Qmix: Monotonic value function factorization for deep multi-agent reinforcement learning","volume-title":"Proc. ICML","author":"Rashid","year":"2018"},{"key":"ref16","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning","volume-title":"Proc. AAMAS","author":"Sunehag","year":"2018"},{"key":"ref17","first-page":"1146","article-title":"Stabilizing experience replay for deep multi-agent reinforcement learning","volume-title":"Proc. ICML","author":"Rashid","year":"2017"},{"key":"ref18","first-page":"1","article-title":"Mutual-information regularized multi-agent policy iteration","volume-title":"Proc. NeurIPS","author":"Wang","year":"2023"},{"key":"ref19","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. NeurIPS","author":"Lowe","year":"2017"},{"key":"ref20","first-page":"40","article-title":"A variational approach to mutual information-based coordination for multi-agent reinforcement learning","volume-title":"Proc. AAMAS","author":"Kim","year":"2023"},{"key":"ref21","first-page":"1","article-title":"Attention-guided contrastive role representations for multi-agent reinforcement learning","volume-title":"Proc. ICLR","author":"Hu","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2023.3268076"},{"key":"ref23","first-page":"3040","article-title":"Social influence as intrinsic motivation for multi-agent deep reinforcement learning","volume-title":"Proc. ICML","author":"Jaques","year":"2019"},{"key":"ref24","first-page":"575","article-title":"Learning latent representations to influence multi-agent interaction","volume-title":"Proc. CoRL","author":"Xie","year":"2021"},{"key":"ref25","first-page":"1","article-title":"LIEF: Learning to influence through evaluative feedback","volume-title":"Proc. AAMAS","author":"Merhej","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29693"},{"key":"ref27","first-page":"1","article-title":"Generating diverse cooperative agents by learning incompatible policies","volume-title":"Proc. ICLR","author":"Rujikorn","year":"2023"},{"key":"ref28","first-page":"5711","article-title":"Self-organized group for cooperative multi-agent reinforcement learning","volume-title":"Proc. NeurIPS","author":"Shao","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29705"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11492"},{"key":"ref31","first-page":"12979","article-title":"PMIC: Improving multi-agent reinforcement learning with progressive mutual information collaboration","volume-title":"Proc. ICML","author":"Li","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-94662-3_12"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref34","first-page":"32438","article-title":"Rethinking individual global max in cooperative multi-agent reinforcement learning","volume-title":"Proc. NeurIPS","author":"Hong","year":"2022"},{"key":"ref35","article-title":"Deep multi-agent reinforcement learning for decentralized continuous cooperative control","author":"Schroeder de Witt","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref38","first-page":"7613","article-title":"Maven: Multi-agent variational exploration","volume-title":"Proc. NeurIPS","author":"Mahajan","year":"2019"},{"key":"ref39","first-page":"531","article-title":"Mutual information neural estimation","volume-title":"Proc. ICML","author":"Belghazi","year":"2018"},{"key":"ref40","first-page":"1779","article-title":"Club: A contrastive log-ratio upper bound of mutual information","volume-title":"Proc. ICML","author":"Cheng","year":"2020"},{"key":"ref41","first-page":"1155","article-title":"A game-theoretic model and best-response learning method for ad hoc coordination in multiagent systems","volume-title":"Proc. AAMAS","author":"Albrecht","year":"2013"},{"key":"ref42","first-page":"2186","article-title":"The starcraft multi-agent challenge","volume-title":"Proc. AAMAS","author":"Samvelyan","year":"2019"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7274989\/11288412\/11015844.pdf?arnumber=11015844","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T18:33:05Z","timestamp":1765909985000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11015844\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":42,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2025.3574031","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}