{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:44:29Z","timestamp":1782798269952,"version":"3.54.5"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Research Foundation of Korea (NRF) grant funded by Korean Government [Ministry of Science and ICT (MSIT)]","award":["RS-2024-00456065"],"award-info":[{"award-number":["RS-2024-00456065"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3704367","type":"journal-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T19:44:44Z","timestamp":1781639084000},"page":"95650-95664","source":"Crossref","is-referenced-by-count":0,"title":["Scalable Multi-Agent Reinforcement Learning With Permutation-Free Networks"],"prefix":"10.1109","volume":"14","author":[{"given":"Hyunwoo","family":"Park","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, University of Seoul, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baekryun","family":"Seong","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, University of Seoul, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5406-5104","authenticated-orcid":false,"given":"Sang-Ki","family":"Ko","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, University of Seoul, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref6","first-page":"4299","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst.","volume":"30","author":"Christiano"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"ref8","article-title":"DeepSeek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv:2501.12948"},{"key":"ref9","first-page":"8113","article-title":"Credit assignment for collective multiagent RL with global rewards","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst.","volume":"31","author":"Nguyen"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-008-9062-9"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.65109\/ixua6834"},{"key":"ref12","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"Rashid","year":"2018","journal-title":"arXiv:1803.11485"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6221"},{"key":"ref14","first-page":"12979","article-title":"PMIC: Improving multi-agent reinforcement learning with progressive mutual information collaboration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1201"},{"key":"ref16","first-page":"590","article-title":"PIC: Permutation invariant critic for multi-agent deep reinforcement learning","volume-title":"Proc. 3rd Annu. Conf. Robot Learn.","author":"Liu"},{"key":"ref17","first-page":"1","article-title":"UPDeT: Universal multi-agent RL via policy decoupling with transformers","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref18","first-page":"1","article-title":"Boosting multiagent reinforcement learning via permutation invariant and permutation equivariant networks","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Hao"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341303"},{"key":"ref20","article-title":"HyperNetworks","author":"Ha","year":"2016","journal-title":"arXiv:1609.09106"},{"key":"ref21","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"Lowe","year":"2017","journal-title":"arXiv:1706.02275"},{"key":"ref22","article-title":"An introduction to centralized training for decentralized execution in cooperative multi-agent reinforcement learning","author":"Amato","year":"2024","journal-title":"arXiv:2409.03052"},{"key":"ref23","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv:1706.05296"},{"key":"ref24","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"Son","year":"2019","journal-title":"arXiv:1905.05408"},{"key":"ref25","article-title":"Rethinking the implementation tricks and monotonicity constraint in cooperative multi-agent reinforcement learning","author":"Hu","year":"2021","journal-title":"arXiv:2102.03479"},{"key":"ref26","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref27","article-title":"Qatten: A general framework for cooperative multiagent reinforcement learning","author":"Yang","year":"2020","journal-title":"arXiv:2002.03939"},{"key":"ref28","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., Annu. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Rashid"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.65109\/LVZZ5205"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.65109\/LYDV1788"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1301"},{"key":"ref32","article-title":"Permutation invariant policy optimization for mean-field multi-agent reinforcement learning: A principled approach","author":"Li","year":"2021","journal-title":"arXiv:2105.08268"},{"key":"ref33","article-title":"Deep sets","author":"Zaheer","year":"2017","journal-title":"arXiv:1703.06114"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref36","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. 5th Int. Conf. Learn. Represent.","author":"Kipf"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3356464.3357707"},{"key":"ref39","article-title":"Multiagent cooperation and competition with deep reinforcement learning","author":"Tampuu","year":"2015","journal-title":"arXiv:1511.08779"},{"key":"ref40","article-title":"Towards skilled population curriculum for multi-agent reinforcement learning","author":"Wang","year":"2023","journal-title":"arXiv:2302.03429"},{"key":"ref41","first-page":"1","article-title":"Evolutionary population curriculum for scaling multi-agent reinforcement learning","volume-title":"Proc. 8th Int. Conf. Learn. Represent.","author":"Long"},{"key":"ref42","first-page":"9681","article-title":"Variational automatic curriculum learning for sparse-reward cooperative multi-agent problems","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 34: Annu. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref45","first-page":"3744","article-title":"Set transformer: A framework for attention-based permutation-invariant neural networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00357"},{"key":"ref47","first-page":"35","article-title":"Hydra attention: Efficient attention with many heads","volume-title":"Proc. Comput. Vis.-ECCV Workshops","author":"Bolya"},{"key":"ref48","first-page":"3991","article-title":"Celebrating diversity in shared multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst.","volume":"34","author":"Li"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11568430.pdf?arnumber=11568430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:10:28Z","timestamp":1782796228000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11568430\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3704367","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}