{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:49:39Z","timestamp":1774630179841,"version":"3.50.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":["62073158"],"award-info":[{"award-number":["62073158"]}],"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":["61673280"],"award-info":[{"award-number":["61673280"]}],"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":["61991404"],"award-info":[{"award-number":["61991404"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Project of Key Field Alliance of Liaoning Province","award":["2019-KF-03-06"],"award-info":[{"award-number":["2019-KF-03-06"]}]},{"name":"Research Program of the Liaoning Liaohe Laboratory","award":["LLL23ZZ-05-01"],"award-info":[{"award-number":["LLL23ZZ-05-01"]}]},{"DOI":"10.13039\/501100019033","name":"Key Research and Development Program of Liaoning Province","doi-asserted-by":"publisher","award":["2023JH26\/10200011"],"award-info":[{"award-number":["2023JH26\/10200011"]}],"id":[{"id":"10.13039\/501100019033","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Project of Liaoning Petrochemical University","award":["2018XJJ-005"],"award-info":[{"award-number":["2018XJJ-005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tcyb.2024.3440333","type":"journal-article","created":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T17:26:45Z","timestamp":1727198805000},"page":"6545-6558","source":"Crossref","is-referenced-by-count":12,"title":["Reinforcement Learning for Synchronization of Heterogeneous Multiagent Systems by Improved <i>Q<\/i>-Functions"],"prefix":"10.1109","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9985-6308","authenticated-orcid":false,"given":"Jinna","family":"Li","sequence":"first","affiliation":[{"name":"School of Information and Control Engineering, Liaoning Petrochemical University, Liaoning, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3092-977X","authenticated-orcid":false,"given":"Lin","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, Liaoning Petrochemical University, Liaoning, China"}]},{"given":"Weiran","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, Liaoning Petrochemical University, Liaoning, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4623-1483","authenticated-orcid":false,"given":"Tianyou","family":"Chai","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4074-1615","authenticated-orcid":false,"given":"Frank L.","family":"Lewis","sequence":"additional","affiliation":[{"name":"UTA Research Institute, The University of Texas at Arlington, Arlington, TX, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2941498"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3027653"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123843"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aav2975"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3284078"},{"key":"ref9","article-title":"Combining policy gradient and Q-learning","author":"O\u2019Donoghue","year":"2017","journal-title":"arXiv:1611.01626"},{"key":"ref10","first-page":"3185","article-title":"Finite-time analysis of asynchronous stochastic approximation and Q-learning","volume-title":"Proc. 33rd Conf. Learn. Theory","author":"Qu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2970969"},{"key":"ref12","first-page":"1","article-title":"Actor\u2013critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Konda"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2927410"},{"key":"ref14","article-title":"Sample efficient actor\u2013critic with experience replay","author":"Wang","year":"2017","journal-title":"arXiv:1611.01224"},{"key":"ref15","article-title":"Q-Prop: Sample-efficient policy gradient with an off-policy critic","author":"Gu","year":"2017","journal-title":"arXiv:1611.02247"},{"key":"ref16","article-title":"Interpolated policy gradient: Merging on-policy and off-policy gradient estimation for deep reinforcement learning","volume-title":"arXiv:1706.00387","author":"Gu","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2832025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2023.114367"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2021.3065654"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3227313"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2609500"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2024.3386678"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-015-3203-x"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.047"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2016.2542134"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3400879"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2023.3344535"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.05.074"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2542923"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3164977"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611971132","volume-title":"Dynamic Noncooperative Game Theory","author":"Ba\u015far","year":"1998"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2623859"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2013.11.028"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.109576"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3015767"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2751018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3384621"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2023.3318525"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3089768"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.12.009"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221036\/10738842\/10690164.pdf?arnumber=10690164","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:23Z","timestamp":1732665623000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10690164\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":41,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2024.3440333","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}