{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T10:50:50Z","timestamp":1782989450200,"version":"3.54.5"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"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":["62476133"],"award-info":[{"award-number":["62476133"]}],"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":["62006119"],"award-info":[{"award-number":["62006119"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"fundamental research funds for the central universities","doi-asserted-by":"publisher","award":["30919011232"],"award-info":[{"award-number":["30919011232"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2022LZH003"],"award-info":[{"award-number":["ZR2022LZH003"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tnnls.2024.3455422","type":"journal-article","created":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T13:25:43Z","timestamp":1726838743000},"page":"12521-12534","source":"Crossref","is-referenced-by-count":6,"title":["TVDO: Tchebycheff Value-Decomposition Optimization for Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0810-2324","authenticated-orcid":false,"given":"Xiaoliang","family":"Hu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengcheng","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0412-5858","authenticated-orcid":false,"given":"Yadong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4817-0618","authenticated-orcid":false,"given":"Guangyu","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0543-4196","authenticated-orcid":false,"given":"Zhen","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4800-832X","authenticated-orcid":false,"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3158085"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3215774"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3220798"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2997896"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04357-7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3172168"},{"key":"ref9","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv:1912.06680"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2663-y"},{"key":"ref11","article-title":"Smarts: Scalable multi-agent reinforcement learning training school for autonomous driving","author":"Zhou","year":"2020","journal-title":"arXiv:2010.09776"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref13","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref15","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. 17th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Sunehag"},{"key":"ref16","first-page":"4295","article-title":"QMix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref17","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":"ref18","article-title":"Qatten: A general framework for cooperative multiagent reinforcement learning","author":"Yang","year":"2020","journal-title":"arXiv:2002.03939"},{"key":"ref19","article-title":"Qplex: Duplex dueling multi-agent Q-learning","author":"Wang","year":"2021","journal-title":"arXiv:2008.01062"},{"key":"ref20","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":"ref21","first-page":"9945","article-title":"DFAC framework: Factorizing the value function via quantile mixture for multi-agent distributional Q-learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20915"},{"key":"ref23","first-page":"5471","article-title":"Resq: A residual q function-based approach for multi-agent reinforcement learning value factorization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Shen"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3172572"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2002.802873"},{"key":"ref26","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","volume-title":"Proc. 15th Nat.\/10th Conf. Artif. Intell.\/Innov. Appl. Artif. Intell.","author":"Claus"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.880330"},{"key":"ref28","article-title":"The StarCraft multi-agent challenge","author":"Samvelyan","year":"2019","journal-title":"arXiv:1902.04043"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref30","first-page":"1","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Iqbal"},{"key":"ref31","article-title":"FACMAC: Factored multi-agent centralised policy gradients","author":"Peng","year":"2020","journal-title":"arXiv:2003.06709"},{"key":"ref32","article-title":"Off-policy multi-agent decomposed policy gradients","author":"Wang","year":"2020","journal-title":"arXiv:2007.12322"},{"key":"ref33","first-page":"5541","article-title":"A policy gradient algorithm for learning to learn in multiagent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref34","first-page":"12491","article-title":"Fop: Factorizing optimal joint policy of maximum-entropy multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref35","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3139138"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3234049"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.01.031"},{"key":"ref40","first-page":"1","article-title":"Maven: Multi-agent variational exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mahajan"},{"key":"ref41","first-page":"1","article-title":"On constrained Boolean Pareto optimization","volume-title":"Proc. 24th Int. Joint Conf. Artif. Intell.","author":"Qian"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref43","first-page":"6826","article-title":"Cooperative exploration for multi-agent deep reinforcement learning","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Liu"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11073756\/10684726.pdf?arnumber=10684726","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T17:49:05Z","timestamp":1752169745000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10684726\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":43,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3455422","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}