{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T19:47:14Z","timestamp":1786132034366,"version":"build-2736575974"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"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":"crossref","award":["62125305"],"award-info":[{"award-number":["62125305"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China","award":["JYB2025XDXM210"],"award-info":[{"award-number":["JYB2025XDXM210"]}]},{"DOI":"10.13039\/501100007128","name":"Natural Science Foundation of Shaanxi Province","doi-asserted-by":"crossref","award":["2025SYSSYSZD-083"],"award-info":[{"award-number":["2025SYSSYSZD-083"]}],"id":[{"id":"10.13039\/501100007128","id-type":"DOI","asserted-by":"crossref"}]},{"name":"State Grid Corporation of China Science and Technology Projects","award":["52060025005B-439-ZN"],"award-info":[{"award-number":["52060025005B-439-ZN"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tpami.2026.3683517","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:36:20Z","timestamp":1776108980000},"page":"10299-10315","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Value Decomposition With Target Transformation in Cooperative Multi-Agent Reinforcement Learning"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3110-8618","authenticated-orcid":false,"given":"Zeyang","family":"Liu","sequence":"first","affiliation":[{"name":"Xi\u2019an Jiaotong University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lipeng","family":"Wan","sequence":"additional","affiliation":[{"name":"Xi\u2019an Jiaotong University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiguang","family":"Sun","sequence":"additional","affiliation":[{"name":"Xi\u2019an Jiaotong University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Sui","sequence":"additional","affiliation":[{"name":"Xi\u2019an Jiaotong University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5226-963X","authenticated-orcid":false,"given":"Xingyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Xi\u2019an Jiaotong University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3422-944X","authenticated-orcid":false,"given":"Xuguang","family":"Lan","sequence":"additional","affiliation":[{"name":"Xi\u2019an Jiaotong University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1608-8257","authenticated-orcid":false,"given":"Nanning","family":"Zheng","sequence":"additional","affiliation":[{"name":"Xi\u2019an Jiaotong University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3268082"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/s23062997"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2893683"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s43684-022-00023-5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.3048477"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/jpm12020309"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2020.107230"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3051163"},{"key":"ref9","first-page":"2145","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Foerster"},{"key":"ref10","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.01.031"},{"key":"ref14","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":"ref15","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":"ref16","first-page":"7613","article-title":"MAVEN: Multi-agent variational exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mahajan"},{"key":"ref17","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.","author":"Rashid"},{"key":"ref18","first-page":"3930","article-title":"UNEVEN: Universal value exploration for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gupta"},{"key":"ref19","first-page":"3235","article-title":"Efficient communication in multi-agent reinforcement learning via variance based control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref20","first-page":"1","article-title":"Learning nearly decomposable value functions via communication minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i9.21179"},{"key":"ref22","first-page":"1","article-title":"Influence-based multi-agent exploration","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref23","first-page":"3757","article-title":"Episodic multi-agent reinforcement learning with curiosity-driven exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zheng"},{"key":"ref24","first-page":"10041","article-title":"MASER: Multi-agent reinforcement learning with subgoals generated from experience replay buffer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jeon"},{"key":"ref25","first-page":"9876","article-title":"ROMA: Multi-agent reinforcement learning with emergent roles","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref26","first-page":"1","article-title":"RODE: Learning roles to decompose multi-agent tasks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26390"},{"key":"ref28","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref29","first-page":"7301","article-title":"Tesseract: Tensorised actors for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mahajan"},{"key":"ref30","first-page":"980","article-title":"Deep coordination graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"B\u00f6hmer"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.65109\/LVZZ5205"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1634"},{"key":"ref33","first-page":"1","article-title":"Context-aware sparse deep coordination graphs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.65109\/JSRC7365"},{"key":"ref36","first-page":"1","article-title":"Exploration by random network distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Burda"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295309"},{"key":"ref38","first-page":"15220","article-title":"How to stay curious while avoiding noisy TVs using aleatoric uncertainty estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mavor-Parker"},{"key":"ref39","article-title":"Prioritized experience replay","author":"Schaul","year":"2015"},{"key":"ref40","article-title":"Qatten: A general framework for cooperative multiagent reinforcement learning","author":"Yang","year":"2020"},{"key":"ref41","first-page":"10706","article-title":"Q-value path decomposition for deep multiagent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3089493"},{"key":"ref43","first-page":"12843","article-title":"Deconfounded value decomposition for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26370"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.65109\/czoy2835"},{"key":"ref46","first-page":"24963","article-title":"Self-organized polynomial-time coordination graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref47","article-title":"An algorithm for distributed reinforcement learning in cooperative multiagent systems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lauer"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399095"},{"issue":"1","key":"ref49","first-page":"2914","article-title":"Lenient learning in independent-learner stochastic cooperative games","volume":"17","author":"Wei","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0395"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3233"},{"key":"ref52","first-page":"22512","article-title":"Greedy based value representation for optimal coordination in multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wan"},{"key":"ref53","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref54","first-page":"1","article-title":"DOP: Off-policy multi-agent decomposed policy gradients","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1787"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1201"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11643729\/11480798.pdf?arnumber=11480798","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T19:08:20Z","timestamp":1786129700000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11480798\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":56,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3683517","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}