{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T00:07:13Z","timestamp":1780618033433,"version":"3.54.1"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tcyb.2022.3179950","type":"journal-article","created":{"date-parts":[[2022,6,22]],"date-time":"2022-06-22T19:44:04Z","timestamp":1655927044000},"page":"5424-5435","source":"Crossref","is-referenced-by-count":12,"title":["PLC-Informed Distributed Game Theoretic Learning of Energy-Optimal Production Policies"],"prefix":"10.1109","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9273-8966","authenticated-orcid":false,"given":"Dorothea","family":"Schwung","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence & Data Science in Automation, University of Applied Sciences, Düsseldorf, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7570-2726","authenticated-orcid":false,"given":"Steve","family":"Yuwono","sequence":"additional","affiliation":[{"name":"Department of Automation Technology, South Westphalia University of Applied Sciences (Campus Soest), Soest, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8405-0977","authenticated-orcid":false,"given":"Andreas","family":"Schwung","sequence":"additional","affiliation":[{"name":"Department of Automation Technology, South Westphalia University of Applied Sciences (Campus Soest), Soest, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5149-5918","authenticated-orcid":false,"given":"Steven X.","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Electrical engineering, University Duisburg-Essen, Duisburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/7219656"},{"key":"ref35","first-page":"1","article-title":"Continuious control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref12","article-title":"A knowledge-based two-population optimization algorithm for distributed energy-efficient parallel machines scheduling","author":"pan","year":"2020","journal-title":"IEEE Trans Cybern"},{"key":"ref34","first-page":"1","article-title":"Distilling policy distillation","author":"czarnecki","year":"2019","journal-title":"Proc Int Conf Artif Intell Stat"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2018.02.004"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2688452"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2013.2256731"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3075183"},{"key":"ref31","first-page":"5694","article-title":"Imagination-augmented agents for deep reinforcement learning","author":"racani\u00e8re","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref30","first-page":"1087","article-title":"Mix & match agent curricula for reinforcement learning","author":"czarnecki","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1515\/auto-2017-0094"},{"key":"ref33","first-page":"4499","article-title":"Distral: Robust multitask reinforcement learning","author":"teh","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref10","article-title":"Kickstarting deep reinforcement learning","author":"schmitt","year":"2018","journal-title":"arXiv 1803 03835"},{"key":"ref32","article-title":"Policy distillation","author":"rusu","year":"2015","journal-title":"arXiv 1511 06295"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2018.01.003"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2015.08.004"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2964955"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2771827"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2964301"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2013.2294155"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2950262"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21629\/JSEE.2018.02.13"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2017.2652919"},{"key":"ref25","first-page":"4063","article-title":"On-line energy optimization of hybrid production systems using actor-critic reinforcement learning","author":"schwung","year":"2019","journal-title":"Proc Int Conf Syst Man Cybern"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2828798"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2908934"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2932082"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2177069"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1587\/transcom.E98.B.1804"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.08.037"},{"key":"ref8","author":"l\u00e3","year":"2016","journal-title":"Potential Game Theory Applications in Radio Resource Allocation"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2013.2257780"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3006620"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974287"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IS.2018.8710460"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2551693"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1006\/game.1996.0044"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/10223305\/09804345.pdf?arnumber=9804345","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T18:15:28Z","timestamp":1693851328000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9804345\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":37,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2022.3179950","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}