{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T03:48:15Z","timestamp":1761709695983,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"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":[],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1109\/smc.2019.8914088","type":"proceedings-article","created":{"date-parts":[[2019,11,29]],"date-time":"2019-11-29T15:09:34Z","timestamp":1575040174000},"page":"4063-4068","source":"Crossref","is-referenced-by-count":9,"title":["Self-Optimization in Smart Production Systems using Distributed Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Dorothea","family":"Schwung","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Madhav","family":"Modali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Schwung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IS.2018.8710466"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IS.2018.8710460"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/INDIN.2017.8104757"},{"key":"ref15","article-title":"Continuious Control with Deep Reinforcement Learning","author":"lillicrap","year":"2016","journal-title":"Proc of International Conference on Learning Representations (ICLR) 2016"},{"key":"ref16","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"99","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0019-9958(77)90354-0"},{"key":"ref18","first-page":"1928","article-title":"Asynchronous Methods for Deep Reinforcement Learning","volume":"48","author":"mnih","year":"2016","journal-title":"Proceedings of The 33rd International Conference on Machine Learning PMLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2018.01.003"},{"key":"ref28","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","author":"omidshafiei","year":"2017","journal-title":"In Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2009.2027013"},{"key":"ref27","article-title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning Based On Team Reward","author":"sunehag","year":"2017","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/21693277.2016.1192517"},{"key":"ref29","article-title":"Adam: A Method for Stochastic Optimization","author":"kingma","year":"2015","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/en8077243"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2013.05.060"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2015.08.004"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/INDIN.2017.8104776"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1515\/auto-2015-0015"},{"key":"ref20","article-title":"Batch normalization: Accelerating deep network training byreducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proceedings of The 33rd International Conference on Machine Learning PMLR"},{"article-title":"Multi-Agent Reinforcement Learning: A Report on Challenges and Approaches","year":"2018","author":"kapoor","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399095"},{"key":"ref23","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","author":"lauer","year":"2000","journal-title":"Proc 17th Int Conf Machine Learning"},{"key":"ref26","article-title":"Counterfactual Multi-Agent Policy Gradients","author":"foerster","year":"2017","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref25","article-title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","author":"lowe","year":"2017","journal-title":"Proc of the 31st Conference on Neural Information Processing Systems"}],"event":{"name":"2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)","start":{"date-parts":[[2019,10,6]]},"location":"Bari, Italy","end":{"date-parts":[[2019,10,9]]}},"container-title":["2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8906183\/8913838\/08914088.pdf?arnumber=8914088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T15:21:59Z","timestamp":1658157719000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8914088\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/smc.2019.8914088","relation":{},"subject":[],"published":{"date-parts":[[2019,10]]}}}