{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T12:27:04Z","timestamp":1792153624583,"version":"4.4.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026,1]]},"DOI":"10.1109\/tcyb.2025.3610707","type":"journal-article","created":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T17:56:13Z","timestamp":1758822973000},"page":"3-14","source":"Crossref","is-referenced-by-count":4,"title":["Integrating Deep Model-Based Learning With Modular State-Based Stackelberg Games for Self-Optimizing Distributed Production Systems"],"prefix":"10.1109","volume":"56","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7570-2726","authenticated-orcid":false,"given":"Steve","family":"Yuwono","sequence":"first","affiliation":[{"name":"Automation Technology and Learning Systems, South Westphalia University of Applied Sciences, 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":"Automation Technology and Learning Systems, South Westphalia University of Applied Sciences, Soest, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9273-8966","authenticated-orcid":false,"given":"Dorothea","family":"Schwung","sequence":"additional","affiliation":[{"name":"Artificial Intelligence and Data Science in Automation Technology, Hochschule Düsseldorf University of Applied Sciences, Düsseldorf, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-024-02682-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-024-00944-3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-51615-5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/arm92050037"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-024-00985-8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119456"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2025.3558515"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2015.06.034"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2025.3561585"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.08.037"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2551693"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3006620"},{"key":"ref13","first-page":"3133","article-title":"Implicit learning dynamics in Stackelberg games: Equilibria characterization, convergence analysis, and empirical study","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Fiez"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF00935665"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12586-7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2025.03.025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IECON55916.2024.10905619"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.dajour.2023.100165"},{"key":"ref19","article-title":"World models","author":"Ha","year":"2018","journal-title":"arXiv:1803.10122"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2023.10.003"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ETFA54631.2023.10275577"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-27015-5_50"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2022.06.008"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.109"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110547"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3179950"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/DSLW51110.2021.9523403"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2878318"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CDS49703.2020.00051"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1002\/asjc.2830"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3028378"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3199211"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-51971-1_5"},{"key":"ref35","article-title":"Towards a simple approach to multi-step model-based reinforcement learning","author":"Asadi","year":"2018","journal-title":"arXiv:1811.00128"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9590"},{"key":"ref37","first-page":"776","article-title":"Multi-agent reinforcement learning with multi-step generative models","volume-title":"Proc. Conf. Robot Learn.","author":"Krupnik"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1587\/transcom.E98.B.1804"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2021.107382"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/11840817_66"},{"key":"ref42","article-title":"Are transformers universal approximators of sequence-to-sequence functions?","author":"Yun","year":"2020","journal-title":"arXiv:1912.10077"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2022.100341"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ONCON60463.2023.10431280"},{"issue":"7","key":"ref45","first-page":"579","article-title":"Multilayer perceptron and neural networks","volume":"8","author":"Popescu","year":"2009","journal-title":"WSEAS Trans. Circuits Syst."},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.79.8.2554.PMC346238.PMID6953413"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref48","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv:1412.3555"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3187702"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3119853"},{"key":"ref54","volume-title":"Model Predictive Control: Theory, Computation, and Design","volume":"2","author":"Rawlings","year":"2017"},{"key":"ref55","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2019","journal-title":"arXiv:1509.02971"},{"key":"ref56","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref57","article-title":"Transfer learning of state-based potential games for process optimization in decentralized manufacturing systems","author":"Yuwono","year":"2024","journal-title":"arXiv:2408.05992"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221036\/11306180\/11179859.pdf?arnumber=11179859","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T18:42:34Z","timestamp":1766428954000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11179859\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":57,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2025.3610707","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}