{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T11:07:40Z","timestamp":1783940860034,"version":"3.55.0"},"reference-count":52,"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":["Neurocomputing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neucom.2026.134437","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T16:05:10Z","timestamp":1783440310000},"page":"134437","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Scalable multi-agent reinforcement learning with group interaction-based role adaptation"],"prefix":"10.1016","volume":"700","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2618-770X","authenticated-orcid":false,"given":"Shiwei","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengke","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangfeng","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaorong","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134437_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.112147","article-title":"RT-FedFlow: an efficient framework for real-time traffic signal optimization using federated multi-agent reinforcement learning","volume":"161","author":"Akbar","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.neucom.2026.134437_bib0010","article-title":"Reinforcement learning-based multi-agent systems for intelligent urban traffic signal optimization","volume":"10","author":"Joshi","year":"2025","journal-title":"J. Artif. Intell. Mach. Learn. Soft Comput."},{"key":"10.1016\/j.neucom.2026.134437_bib0015","author":"Bacchiani"},{"key":"10.1016\/j.neucom.2026.134437_bib0020","series-title":"2023 IEEE International Conference on Smart Computing (SMARTCOMP)","first-page":"149","article-title":"Cooperative multi-agent reinforcement learning for large scale variable speed limit control","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134437_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130065","article-title":"GlobalLight: exploring global influence in multi-agent deep reinforcement learning for large-scale traffic signal control","volume":"637","author":"Liu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134437_bib0030","author":"Repasky"},{"key":"10.1016\/j.neucom.2026.134437_bib0035","author":"Sivagnanam"},{"key":"10.1016\/j.neucom.2026.134437_bib0040","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1109\/TWC.2019.2935201","article-title":"Multi-agent reinforcement learning-based resource allocation for UAV networks","volume":"19","author":"Cui","year":"2019","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"10.1016\/j.neucom.2026.134437_bib0045","doi-asserted-by":"crossref","first-page":"2005","DOI":"10.1109\/TITS.2023.3314929","article-title":"Multi-agent reinforcement learning for slicing resource allocation in vehicular networks","volume":"25","author":"Cui","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.neucom.2026.134437_bib0050","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134437_bib0055","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Counterfactual multi-agent policy gradients","volume":"Vol. 32","author":"Foerster","year":"2018"},{"key":"10.1016\/j.neucom.2026.134437_bib0060","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134437_bib0065","doi-asserted-by":"crossref","first-page":"6369","DOI":"10.1007\/s00521-024-10651-y","article-title":"Composite neural learning-based adaptive actuator failure compensation control for full-state constrained autonomous surface vehicle","volume":"37","author":"Song","year":"2025","journal-title":"Neural Comput. Appl."},{"key":"10.1016\/j.neucom.2026.134437_bib0070","series-title":"Conference on Robot Learning","first-page":"823","article-title":"Graph policy gradients for large scale robot control","author":"Khan","year":"2020"},{"key":"10.1016\/j.neucom.2026.134437_bib0075","series-title":"2023 IEEE 12th International Conference on Cloud Networking (CloudNet)","first-page":"247","article-title":"ROMA: resilient multi-agent reinforcement learning with dynamic participating agents","author":"Tang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134437_bib0080","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128015","article-title":"An overview: attention mechanisms in multi-agent reinforcement learning","volume":"598","author":"Hu","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134437_bib0085","author":"Wang"},{"key":"10.1016\/j.neucom.2026.134437_bib0090","series-title":"Proceedings of the 37th International Conference on Machine Learning","first-page":"9876","article-title":"ROMA: multi-agent reinforcement learning with emergent roles","author":"Wang","year":"2020"},{"key":"10.1016\/j.neucom.2026.134437_bib0095","article-title":"ROCO: role-oriented communication for efficient multi-agent reinforcement learning","author":"Xie","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.neucom.2026.134437_bib0100","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113811","article-title":"Role play: learning adaptive role-specific strategies in multi-agent interactions","author":"Long","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.neucom.2026.134437_bib0105","series-title":"Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems","doi-asserted-by":"crossref","first-page":"2085","DOI":"10.65109\/JSRC7365","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"Sunehag","year":"2018"},{"key":"10.1016\/j.neucom.2026.134437_bib0110","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"11308","article-title":"Resilient multi-agent reinforcement learning with adversarial value decomposition","volume":"Vol. 35","author":"Phan","year":"2021"},{"key":"10.1016\/j.neucom.2026.134437_bib0115","author":"Long"},{"key":"10.1016\/j.neucom.2026.134437_bib0120","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"7293","article-title":"From few to more: large-scale dynamic multiagent curriculum learning","volume":"Vol. 34","author":"Wang","year":"2020"},{"key":"10.1016\/j.neucom.2026.134437_bib0125","doi-asserted-by":"crossref","first-page":"2093","DOI":"10.1109\/TNNLS.2021.3105869","article-title":"UNMAS: multiagent reinforcement learning for unshaped cooperative scenarios","volume":"34","author":"Chai","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2026.134437_bib0130","author":"Agarwal"},{"key":"10.1016\/j.neucom.2026.134437_bib0135","doi-asserted-by":"crossref","first-page":"4","DOI":"10.3390\/e27010004","article-title":"Multi-agent hierarchical graph attention actor\u2013critic reinforcement learning","volume":"27","author":"Li","year":"2024","journal-title":"Entropy"},{"key":"10.1016\/j.neucom.2026.134437_bib0140","article-title":"Heterogeneous multi-agent reinforcement learning for zero-shot scalable collaboration","author":"Guo","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134437_bib0145","series-title":"Proceedings of the 2019 4th International Conference on Advances in Robotics","first-page":"1","article-title":"Parameter sharing reinforcement learning architecture for multi agent driving","author":"Kaushik","year":"2019"},{"key":"10.1016\/j.neucom.2026.134437_bib0150","series-title":"2025 IEEE International Conference on Real-time Computing and Robotics (RCAR)","first-page":"827","article-title":"Scalable multi-agent reinforcement learning: adaptive policies with dynamic agent and target","author":"Guo","year":"2025"},{"key":"10.1016\/j.neucom.2026.134437_bib0155","author":"Bettini"},{"key":"10.1016\/j.neucom.2026.134437_bib0160","series-title":"Using representation learning for scalable multi-agent reinforcement learning in heterogeneous multi-agent systems","author":"Wessels","year":"2025"},{"key":"10.1016\/j.neucom.2026.134437_bib0165","series-title":"Chinese Conference on Swarm Intelligence and Cooperative Control","first-page":"39","article-title":"Multi-agent reinforcement learning algorithm based on role parameter sharing","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134437_bib0170","series-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"6035","article-title":"Adaptive parameter sharing for multi-agent reinforcement learning","author":"Li","year":"2024"},{"key":"10.1016\/j.neucom.2026.134437_bib0175","series-title":"Proceedings Fourth IFCIS International Conference on Cooperative Information Systems. CoopIS 99 (Cat. No. PR00384)","first-page":"325","article-title":"ROPE: role oriented programming environment for multiagent systems","author":"Becht","year":"1999"},{"key":"10.1016\/j.neucom.2026.134437_bib0180","series-title":"International Workshop on Agent-Oriented Software Engineering","first-page":"214","article-title":"From agents to organizations: an organizational view of multi-agent systems","author":"Ferber","year":"2003"},{"key":"10.1016\/j.neucom.2026.134437_bib0185","series-title":"International Conference on Machine Learning","first-page":"1989","article-title":"Scaling multi-agent reinforcement learning with selective parameter sharing","author":"Christianos","year":"2021"},{"key":"10.1016\/j.neucom.2026.134437_bib0190","series-title":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"3128","article-title":"DyPS: dynamic parameter sharing in multi-agent reinforcement learning for spatio-temporal resource allocation","author":"Wang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134437_bib0195","series-title":"ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"Diverse collaboration in multi-agent reinforcement learning via self-adaptive method","author":"Xue","year":"2025"},{"key":"10.1016\/j.neucom.2026.134437_bib0200","first-page":"3991","article-title":"Celebrating diversity in shared multi-agent reinforcement learning","volume":"34","author":"Li","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"2","key":"10.1016\/j.neucom.2026.134437_bib0205","doi-asserted-by":"crossref","first-page":"2051","DOI":"10.1109\/TNNLS.2023.3326744","article-title":"Celebrating diversity with subtask specialization in shared multiagent reinforcement learning","volume":"36","author":"Li","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2026.134437_bib0210","series-title":"A Concise Introduction to Decentralized POMDPs","volume":"vol. 1","author":"Oliehoek","year":"2016"},{"key":"10.1016\/j.neucom.2026.134437_bib0215","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1613\/jair.2447","article-title":"Optimal and approximate Q-value functions for decentralized POMDPs","volume":"32","author":"Oliehoek","year":"2008","journal-title":"J. Artif. Intell. Res."},{"key":"10.1016\/j.neucom.2026.134437_bib0220","series-title":"An Introduction","article-title":"Reinforcement learning","volume":"vol. 1","author":"Sutton","year":"1998"},{"key":"10.1016\/j.neucom.2026.134437_bib0225","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1016\/j.isatra.2024.12.023","article-title":"End-to-end multi-scale residual network with parallel attention mechanism for fault diagnosis under noise and small samples","volume":"157","author":"Sun","year":"2025","journal-title":"ISA Trans."},{"key":"10.1016\/j.neucom.2026.134437_bib0230","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","article-title":"A mathematical theory of communication","volume":"27","author":"Shannon","year":"1948","journal-title":"Bell Syst. Tech. J."},{"key":"10.1016\/j.neucom.2026.134437_bib0235","series-title":"International Conference on Machine Learning","first-page":"5171","article-title":"On variational bounds of mutual information","author":"Poole","year":"2019"},{"key":"10.1016\/j.neucom.2026.134437_bib0240","author":"Alemi"},{"key":"10.1016\/j.neucom.2026.134437_bib0245","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.neucom.2026.134437_bib0250","author":"Schulman"},{"key":"10.1016\/j.neucom.2026.134437_bib0255","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.neucom.2026.134437_bib0260","author":"Hu"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226018357?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226018357?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T10:45:23Z","timestamp":1783939523000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226018357"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":52,"alternative-id":["S0925231226018357"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134437","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Scalable multi-agent reinforcement learning with group interaction-based role adaptation","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134437","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"134437"}}