{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:44:54Z","timestamp":1767339894316,"version":"3.46.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"UniSA Enterprise Fellowship and the Australian Research Council (ARC) Discovery Early Career Researcher Award (DECRA) Fellowship","award":["DE220100265"],"award-info":[{"award-number":["DE220100265"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tnnls.2024.3387397","type":"journal-article","created":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T13:40:16Z","timestamp":1713793216000},"page":"6627-6641","source":"Crossref","is-referenced-by-count":4,"title":["SATF: A Scalable Attentive Transfer Framework for Efficient Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5239-596X","authenticated-orcid":false,"given":"Bin","family":"Chen","sequence":"first","affiliation":[{"name":"STEM, University of South Australia, Adelaide, SA, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3656-0328","authenticated-orcid":false,"given":"Zehong","family":"Cao","sequence":"additional","affiliation":[{"name":"STEM, University of South Australia, Adelaide, SA, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1214-6317","authenticated-orcid":false,"given":"Quan","family":"Bai","sequence":"additional","affiliation":[{"name":"School of ICT, University of Tasmania, Hobart, TAS, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071959"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2990598"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3103642"},{"key":"ref4","first-page":"2095","article-title":"Hierarchical and non-hierarchical multi-agent interactions based on unity reinforcement learning","volume-title":"Proc. 19th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Cao"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"journal-title":"arXiv:1912.06680","article-title":"DOTA 2 with large scale deep reinforcement learning","year":"2019","key":"ref6"},{"key":"ref7","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref8","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref10","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe"},{"key":"ref11","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. Int. Conf. Auto. Agents Multiagent Syst.","author":"Sunehag"},{"issue":"1","key":"ref12","first-page":"7234","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref14","first-page":"2186","article-title":"The StarCraft multi-agent challenge","volume-title":"Proc. 18th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Samvelyan"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2823329"},{"issue":"5","key":"ref16","first-page":"7293","article-title":"From few to more: Large-scale dynamic multiagent curriculum learning","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"34","author":"Wang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref19","first-page":"10199","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Rashid"},{"key":"ref20","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":"ref21","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref22","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yu"},{"key":"ref23","first-page":"1046","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kuba"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3215774"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3220798"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3146858"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3183865"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11396"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09430-0"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9428"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016128"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_15"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/65"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref35","first-page":"9876","article-title":"ROMA: Multi-agent reinforcement learning with emergent roles","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"issue":"2","key":"ref36","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1109\/TEVC.2023.3268076","article-title":"A multi-agent cooperative learning system with evolution of social roles","volume":"28","author":"Hou","year":"2024","journal-title":"IEEE Trans. Evol. Comput."},{"key":"ref37","first-page":"2607","article-title":"Improving cooperative multi-agent exploration via surprise minimization and social influence maximization","volume-title":"Proc. Int. Conf. Auto. Agents Multiagent Syst.","author":"Sun"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2023.3272386"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2023.3316697"},{"key":"ref40","first-page":"2460","article-title":"Portal: Automatic curricula generation for multiagent reinforcement learning","volume-title":"Proc. Int. Conf. Auto. Agents Multiagent Syst.","author":"Wu"},{"key":"ref41","first-page":"78514","article-title":"Decompose a task into generalizable subtasks in multi-agent reinforcement learning","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Tian"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3309608"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3243557"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-28929-8","volume-title":"A Concise Introduction to Decentralized POMDPs","author":"Oliehoek","year":"2016"},{"key":"ref45","first-page":"764","article-title":"Coordinated multi-agent reinforcement learning in networked distributed pomdps","volume-title":"Proc. 25th AAAI Conf. Artif. Intell.","author":"Zhang"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"},{"key":"ref48","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"Vinyals","year":"2017","journal-title":"arXiv:1708.04782"},{"issue":"10","key":"ref49","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3505244","article-title":"Transformers in vision: A survey","volume":"54","author":"Khan","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8655(87)90072-9"},{"key":"ref51","article-title":"The StarCraft multi-agent challenge","author":"Samvelyan","year":"2019","journal-title":"arXiv:1902.04043"},{"key":"ref52","first-page":"1438","article-title":"Quicr-learning for multi-agent coordination","volume-title":"Proc. AAAI","author":"Agogino"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"key":"ref54","article-title":"SMACv2: An improved benchmark for cooperative multi-agent reinforcement learning","author":"Ellis","year":"2022","journal-title":"arXiv:2212.07489"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2939-8"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10949581\/10506202.pdf?arnumber=10506202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:37Z","timestamp":1764959977000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10506202\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":55,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3387397","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}