{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T11:40:27Z","timestamp":1770378027966,"version":"3.49.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"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":["62422605"],"award-info":[{"award-number":["62422605"]}],"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":["624B2101"],"award-info":[{"award-number":["624B2101"]}],"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":["92370132"],"award-info":[{"award-number":["92370132"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tcyb.2025.3625137","type":"journal-article","created":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T18:33:34Z","timestamp":1765391614000},"page":"725-738","source":"Crossref","is-referenced-by-count":0,"title":["Signaling-Driven Incentive Communication for Enhanced Multiagent Reinforcement Learning in Dynamic Environments"],"prefix":"10.1109","volume":"56","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2712-9088","authenticated-orcid":false,"given":"Kexing","family":"Peng","sequence":"first","affiliation":[{"name":"School of Computer Science, Nanjing University of Information Science and Technology, Nanjing, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8546-2346","authenticated-orcid":false,"given":"Pengyi","family":"Li","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0422-8235","authenticated-orcid":false,"given":"Jianye","family":"Hao","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3453892"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-48526-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s44287-024-00034-9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-5581-3_33"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3409530"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00879-7"},{"key":"ref7","first-page":"37013","article-title":"Demystifying structural disparity in graph neural networks: Can one size fit all?","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"36","author":"Mao"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.65109\/urcw5545"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jai.2024.02.003"},{"key":"ref11","first-page":"1","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"29","author":"Foerster"},{"key":"ref12","first-page":"2252","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"29","author":"Sukhbaatar"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29438"},{"key":"ref14","first-page":"25584","article-title":"Information design in multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"36","author":"Lin"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3440333"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i9.21179"},{"key":"ref17","first-page":"16957","article-title":"Beyond normal: On the evaluation of mutual information estimators","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"36","author":"Czy\u02d9z"},{"key":"ref18","first-page":"3757","article-title":"Episodic multi-agent reinforcement learning with curiosity-driven exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Zheng"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.65109\/yhuo7761"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3513402"},{"key":"ref24","first-page":"1","article-title":"Exponential topology-enabled scalable communication in multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Li"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120983"},{"issue":"178","key":"ref26","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":"ref27","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":"ref28","first-page":"4403","article-title":"LIIR: Learning individual intrinsic reward in multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"32","author":"Du"},{"key":"ref29","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref30","first-page":"9876","article-title":"ROMA: Multi-agent reinforcement learning with emergent roles","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Wang"},{"key":"ref31","first-page":"1","article-title":"RODE: Learning roles to decompose multi-agent tasks","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.65109\/bsui8234"},{"key":"ref33","first-page":"34791","article-title":"RiskQ: Risk-sensitive multi-agent reinforcement learning value factorization","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"36","author":"Shen"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2024.111557"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3685-3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106101"},{"key":"ref37","first-page":"42200","article-title":"Local optimization achieves global optimality in multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Zhao"},{"key":"ref38","first-page":"1","article-title":"DOP: Off-policy multi-agent decomposed policy gradients","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref39","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Iqbal"},{"key":"ref40","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"30","author":"Lowe"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17203"},{"key":"ref42","article-title":"Qatten: A general framework for cooperative multiagent reinforcement learning","author":"Yang","year":"2020","journal-title":"arXiv:2002.03939"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.65109\/czoy2835"},{"key":"ref44","first-page":"980","article-title":"Deep coordination graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"B\u00f6hmer"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3407760"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3377106"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221036\/11371480\/11296869.pdf?arnumber=11296869","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T20:41:32Z","timestamp":1770324092000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11296869\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":46,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2025.3625137","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}