{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:22:20Z","timestamp":1792786940722,"version":"4.5.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2023YFB4704900"],"award-info":[{"award-number":["2023YFB4704900"]}]},{"name":"National Natural Science Foundation of China","award":["U21A20485"],"award-info":[{"award-number":["U21A20485"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1109\/tpami.2026.3718850","type":"journal-article","created":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T19:03:05Z","timestamp":1785438185000},"page":"14954-14967","source":"Crossref","is-referenced-by-count":1,"title":["Efficient Heterogeneous Exploration With Mutual Policy Divergence Maximization for Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9707-8036","authenticated-orcid":false,"given":"Haowen","family":"Dou","sequence":"first","affiliation":[{"name":"Xi\u2019an Jiaotong University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8929-8127","authenticated-orcid":false,"given":"Lujuan","family":"Dang","sequence":"additional","affiliation":[{"name":"Xi\u2019an Jiaotong University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingfei","family":"Lu","sequence":"additional","affiliation":[{"name":"Xi\u2019an University of Architecture and technology","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangjun","family":"Chen","sequence":"additional","affiliation":[{"name":"Xi\u2019an Jiaotong University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1710-3818","authenticated-orcid":false,"given":"Badong","family":"Chen","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\/TNNLS.2022.3232630"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3146976"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1591"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3146858"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.65109\/JCLE4281"},{"key":"ref7","first-page":"15007","article-title":"On improving model-free algorithms for decentralized multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mao","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3102140"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3283537"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3216203"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2022.3232390"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3396097"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3262592"},{"key":"ref14","first-page":"6863","article-title":"Revisiting some common practices in cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fu","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3347128"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1003814"},{"key":"ref17","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kuba","year":"2022"},{"key":"ref18","first-page":"1","article-title":"Order matters: Agent-by-agent policy optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3399936"},{"key":"ref20","first-page":"13458","article-title":"Settling the variance of multi-agent policy gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kuba","year":"2021"},{"key":"ref21","article-title":"Revisiting parameter sharing in multi-agent deep reinforcement learning","author":"Terry","year":"2020"},{"key":"ref22","first-page":"17455","article-title":"Cooperative heterogeneous deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zheng","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.65109\/slob2372"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3151607"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1201"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802580"},{"key":"ref27","first-page":"61186","article-title":"Optimistic multi-agent policy gradient","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhao","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200726"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3577259"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2428"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.16457"},{"key":"ref32","first-page":"73223","article-title":"MaxinfoRL: Boosting exploration in reinforcement learning through information gain maximization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sukhija","year":"2025"},{"key":"ref33","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","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1787"},{"key":"ref35","first-page":"16829","article-title":"An adaptive entropy-regularization framework for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10649966"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611978520.55"},{"key":"ref38","first-page":"3991","article-title":"Celebrating diversity in shared multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3502176"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3552434"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110864"},{"key":"ref42","article-title":"Reward-free exploration by conditional divergence maximization","author":"Li","year":"2023"},{"key":"ref43","article-title":"Deep multi-agent reinforcement learning for decentralized continuous cooperative control","author":"Witt","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339515"},{"key":"ref46","first-page":"29304","article-title":"Deep reinforcement learning at the edge of the statistical precipice","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Agarwal","year":"2021"},{"key":"ref47","first-page":"30284","article-title":"Generalized Jensen-Shannon divergence loss for learning with noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Englesson","year":"2021"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11723300\/11631673.pdf?arnumber=11631673","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:12:56Z","timestamp":1791486776000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11631673\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":47,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3718850","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":[[2026,11]]}}}