{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T18:02:53Z","timestamp":1784311373627,"version":"3.55.0"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.ins.2026.123771","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:32:35Z","timestamp":1781278355000},"page":"123771","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Dynamic weighted mean field multi-agent reinforcement learning"],"prefix":"10.1016","volume":"755","author":[{"given":"Linyue","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4200-3974","authenticated-orcid":false,"given":"Benke","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiyao","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ins.2026.123771_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111194","article-title":"Optimizing reinforcement learning for large action spaces via generative models: battery pattern selection","volume":"160","author":"Hu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.ins.2026.123771_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.rcim.2023.102628","article-title":"Deep reinforcement learning for solving resource constrained project scheduling problems with resource disruptions","volume":"85","author":"Cai","year":"2024","journal-title":"Robot. Comput.-Integr. Manuf."},{"issue":"5","key":"10.1016\/j.ins.2026.123771_bib0015","first-page":"5274","article-title":"Weighted mean field reinforcement learning for large-scale UAV swarm confrontation","volume":"53","author":"Wang","year":"2023","journal-title":"Appl. Intell."},{"key":"10.1016\/j.ins.2026.123771_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109436","article-title":"Multi-agent dueling Q-learning with mean field and value decomposition","volume":"139","author":"Ding","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.ins.2026.123771_bib0025","author":"Roderick"},{"key":"10.1016\/j.ins.2026.123771_bib0030","series-title":"International Conference on Database Systems for Advanced Applications","first-page":"301","article-title":"Weighted mean-field multi-agent reinforcement learning via reward attribution decomposition","author":"Wu","year":"2022"},{"key":"10.1016\/j.ins.2026.123771_bib0035","author":"Subramanian"},{"key":"10.1016\/j.ins.2026.123771_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2024.120560","article-title":"Adaptive mean field multi-agent reinforcement learning","volume":"669","author":"Wang","year":"2024","journal-title":"Inf. Sci."},{"issue":"2","key":"10.1016\/j.ins.2026.123771_bib0045","article-title":"A weighted mean field reinforcement learning algorithm for large-scale multi-agent collaboration","volume":"3","author":"Yuan","year":"2023","journal-title":"Guid. Navig. Control"},{"key":"10.1016\/j.ins.2026.123771_bib0050","series-title":"International Conference on Machine Learning","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","author":"Yang","year":"2018"},{"key":"10.1016\/j.ins.2026.123771_bib0055","series-title":"Phase Transitions and Critical Phenomena","author":"Stanley","year":"1971"},{"key":"10.1016\/j.ins.2026.123771_bib0060","series-title":"International Conference on Cognitive Systems and Signal Processing","first-page":"309","article-title":"Large-scale multi-agent reinforcement learning based on weighted mean field","author":"Fang","year":"2020"},{"issue":"1","key":"10.1016\/j.ins.2026.123771_bib0065","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1038\/scientificamerican0792-66","article-title":"Genetic algorithms","volume":"267","author":"Holland","year":"1992","journal-title":"Sci. Am."},{"key":"10.1016\/j.ins.2026.123771_bib0070","series-title":"Proceedings of ICNN\u201995-International Conference on Neural Networks","first-page":"1942","article-title":"Particle swarm optimization","volume":"vol. 4","author":"Kennedy","year":"1995"},{"key":"10.1016\/j.ins.2026.123771_bib0075","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2024.121140","article-title":"Greedy deep stochastic configuration networks ensemble with boosting negative correlation learning","volume":"680","author":"Zhang","year":"2024","journal-title":"Inf. Sci."},{"key":"10.1016\/j.ins.2026.123771_bib0080","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112000","article-title":"An evolutionary multi-agent reinforcement learning algorithm for multi-UAV air combat","volume":"299","author":"Wang","year":"2024","journal-title":"Knowl.-based Syst."},{"issue":"5","key":"10.1016\/j.ins.2026.123771_bib0085","doi-asserted-by":"crossref","first-page":"6867","DOI":"10.1007\/s40747-024-01504-1","article-title":"Multi-UAV pursuit-evasion gaming based on PSO-M3DDPG schemes","volume":"10","author":"Zhang","year":"2024","journal-title":"Complex Intell. Syst."},{"key":"10.1016\/j.ins.2026.123771_bib0090","series-title":"Phase Transitions and Critical Phenomena","volume":"vol. 19","author":"Domb","year":"2000"},{"key":"10.1016\/j.ins.2026.123771_bib0095","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2022.109490","article-title":"Spectral richness PSO algorithm for parameter identification of dynamical systems under non-ideal excitation conditions","volume":"128","author":"Cortez","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.ins.2026.123771_bib0100","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.swevo.2012.12.004","article-title":"An improved PSO algorithm with a territorial diversity-preserving scheme and enhanced exploration\u2013exploitation balance","volume":"11","author":"Arani","year":"2013","journal-title":"Swarm Evol. Comput."},{"key":"10.1016\/j.ins.2026.123771_bib0105","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126398","article-title":"t-SNE-PSO: optimizing t-SNE using particle swarm optimization","volume":"269","author":"Allaoui","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.ins.2026.123771_bib0110","doi-asserted-by":"crossref","DOI":"10.1016\/j.swevo.2024.101543","article-title":"Competitive swarm optimizer: a decade survey","volume":"87","author":"Chauhan","year":"2024","journal-title":"Swarm Evol. Comput."},{"key":"10.1016\/j.ins.2026.123771_bib0115","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"MAgent: a many-agent reinforcement learning platform for artificial collective intelligence","volume":"vol. 32","author":"Zheng","year":"2018"},{"key":"10.1016\/j.ins.2026.123771_bib0120","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Emergence of grounded compositional language in multi-agent populations","volume":"vol. 32","author":"Mordatch","year":"2018"},{"key":"10.1016\/j.ins.2026.123771_bib0125","author":"Zhou"},{"key":"10.1016\/j.ins.2026.123771_bib0130","first-page":"24018","article-title":"VAST: value function factorization with variable agent sub-teams","volume":"34","author":"Phan","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"9","key":"10.1016\/j.ins.2026.123771_bib0135","first-page":"9439","article-title":"Decentralized mean field games","volume":"36","author":"Subramanian","year":"2022","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"16","key":"10.1016\/j.ins.2026.123771_bib0140","first-page":"17354","article-title":"Expressive multi-agent communication via identity-aware learning","volume":"38","author":"Du","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.ins.2026.123771_bib0145","series-title":"The First MARW: Multi-Agent AI in the Real World Workshop at AAAI 2025","article-title":"Scaling multi-agent RL through mean field games and incremental learning","author":"Balsells","year":"2025"},{"issue":"1","key":"10.1016\/j.ins.2026.123771_bib0150","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1287\/moor.2022.0055","article-title":"Mean-field multiagent reinforcement learning: a decentralized network approach","volume":"50","author":"Gu","year":"2025","journal-title":"Math. Oper. Res."},{"key":"10.1016\/j.ins.2026.123771_bib0155","first-page":"32","article-title":"Neural temporal-difference learning converges to global optima","author":"Cai","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ins.2026.123771_bib0160","author":"Cayci"},{"key":"10.1016\/j.ins.2026.123771_bib0165","author":"Anand"},{"key":"10.1016\/j.ins.2026.123771_bib0170","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1016\/j.chemolab.2015.08.020","article-title":"Particle swarm optimization (PSO). A tutorial","volume":"149","author":"Marini","year":"2015","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"10.1016\/j.ins.2026.123771_bib0175","series-title":"The World Wide Web Conference","first-page":"983","article-title":"Efficient ridesharing order dispatching with mean field multi-agent reinforcement learning","author":"Li","year":"2019"},{"key":"10.1016\/j.ins.2026.123771_bib0180","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111323","article-title":"QVF: incorporating quantile value function factorization into cooperative multi-agent reinforcement learning","volume":"161","author":"Huang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.ins.2026.123771_bib0185","author":"Jusup"},{"issue":"2","key":"10.1016\/j.ins.2026.123771_bib0190","doi-asserted-by":"crossref","first-page":"2155","DOI":"10.1109\/TNSM.2024.3352014","article-title":"Multi-agent deep reinforcement learning for packet routing in tactical mobile sensor networks","volume":"21","author":"Okine","year":"2024","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"issue":"6","key":"10.1016\/j.ins.2026.123771_bib0195","doi-asserted-by":"crossref","first-page":"8557","DOI":"10.1109\/TNNLS.2022.3230701","article-title":"Depthwise convolution for multi-agent communication with enhanced mean-field approximation","volume":"35","author":"Xie","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.ins.2026.123771_bib0200","author":"Pasztor"},{"key":"10.1016\/j.ins.2026.123771_bib0205","author":"Li"},{"key":"10.1016\/j.ins.2026.123771_bib0210","author":"Subramanian"},{"issue":"10","key":"10.1016\/j.ins.2026.123771_bib0215","first-page":"11744","article-title":"Hierarchical mean-field deep reinforcement learning for large-scale multiagent systems","volume":"37","author":"Yu","year":"2023","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.ins.2026.123771_bib0220","series-title":"International Conference on Machine Learning","first-page":"12078","article-title":"Scalable deep reinforcement learning algorithms for mean field games","author":"Lauriere","year":"2022"}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526007024?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526007024?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T17:05:58Z","timestamp":1784307958000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025526007024"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":44,"alternative-id":["S0020025526007024"],"URL":"https:\/\/doi.org\/10.1016\/j.ins.2026.123771","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Dynamic weighted mean field multi-agent reinforcement learning","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ins.2026.123771","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"123771"}}