{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T11:47:20Z","timestamp":1787312840355,"version":"build-2736575974"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"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"}]},{"name":"Open Project of Key Field Alliance of Liaoning Province","award":["2019-KF-03-06"],"award-info":[{"award-number":["2019-KF-03-06"]}]},{"name":"Project of Liaoning Shihua University","award":["2018XJJ-005"],"award-info":[{"award-number":["2018XJJ-005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2970760","type":"journal-article","created":{"date-parts":[[2020,1,31]],"date-time":"2020-01-31T15:42:07Z","timestamp":1580485327000},"page":"28831-28846","source":"Crossref","is-referenced-by-count":6,"title":["<i>\n                      H\n                      <sub>\u221e<\/sub>\n                    <\/i>\n                    Control for Discrete-Time Multi-Player Systems via Off-Policy Q-Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9985-6308","authenticated-orcid":false,"given":"Jinna","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenfei","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2950262"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1002\/acs.2348"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2011.03.005"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2013.2295351"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2609500"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2496299"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2939384"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.3719"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1109\/MCS.2016.2621461","article-title":"Game theory-based control system algorithms with real-time reinforcement learning: How to solve multiplayer games online","volume":"37","author":"vamvoudakis","year":"2017","journal-title":"IEEE Control Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.05.074"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/9.618250"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2016.12.003"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/9.654912"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(98)80021-6"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.06.096"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.1760"},{"key":"ref15","first-page":"493","article-title":"Approximate dynamic programming for realtime control and neural modelling","author":"werbos","year":"1992","journal-title":"Handbook of Intelligent Control Neural Fuzzy and Adaptive Approaches"},{"key":"ref16","article-title":"Online adaptive optimal control for continuous-time systems","author":"vrabie","year":"2010"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/0020718508961188"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12072"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2319577"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-4757-5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2461023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2799798"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.04.005"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1142\/S2301385016400069"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2006.880135"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2861826"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.02.002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.4590040409"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.02.051"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/9.256331"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.06.008"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/00207178908559623"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2542923"},{"key":"ref48","first-page":"1054","article-title":"Safe and efficient off-policy reinforcement learning","author":"munos","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.12.009"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2300532"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2006.09.019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.05.011"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.05.027"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.02.015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.05.002"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2861945"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.11.041"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.926614"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2441749"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/08977468.pdf?arnumber=8977468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T14:51:19Z","timestamp":1639752679000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8977468\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2970760","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}