{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:16:55Z","timestamp":1787012215393,"version":"build-2736575974"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,7]]},"DOI":"10.1109\/indin.2017.8104770","type":"proceedings-article","created":{"date-parts":[[2017,11,28]],"date-time":"2017-11-28T11:34:58Z","timestamp":1511868898000},"page":"194-199","source":"Crossref","is-referenced-by-count":15,"title":["An application of reinforcement learning algorithms to industrial multi-robot stations for cooperative handling operation"],"prefix":"10.1109","author":[{"given":"Dorothea","family":"Schwung","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabian","family":"Csaplar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Schwung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steven X.","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9120-4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2013.06.025"},{"key":"ref12","author":"kempf","year":"2010","journal-title":"A cognitive control framework for robot supported handling problems Dissertation RWTH Aachen"},{"key":"ref13","author":"knight","year":"2016","journal-title":"A japanese industrial robot can teach itself to perform a task overnight Mit technology review"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1080.0305"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1017\/S026988890500041X"},{"key":"ref18","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","author":"lauer","year":"2000","journal-title":"roceedings of the Seventeenth International Conference on Machine Learning (ICML-2000)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2012.2214134"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.2478\/s13230-011-0017-5","article-title":"Cooperative multi-agent reinforcement learning for multi-component robotic systems: Guidelines for future research","volume":"2","author":"gra\u00f1a","year":"2011","journal-title":"Paladyn Journal of Behavioral Robotics"},{"key":"ref6","author":"lillicrap","year":"2016","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095096"},{"key":"ref8","author":"gu","year":"2016","journal-title":"Deep reinforcement learning for robotic manipulation"},{"key":"ref7","article-title":"An application of reinforcement learning to aerobatic helicopter flight","author":"abbeel","year":"2006","journal-title":"NIPS'06 Proceedings of the 19th International Conference on Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-658-11755-9"},{"key":"ref1","article-title":"Kybernetik und die Intelligenz verteilter Systeme: Nordrhein-Westfalen auf dem Weg zum digitalen Industrieland","author":"jeschke","year":"2014","journal-title":"Clus-termanagement IKT NRW"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00287-006-0077-9"},{"key":"ref20","author":"csaplar","year":"2017","journal-title":"Kollisionserkennung und vermeidung von zwei In-dustrierobotern wäh rend der kooperativen Bearbeitung von Hand-lungsprozessen Bachelorthesis South Westfalia University of Applied Science"},{"key":"ref22","first-page":"659","article-title":"Evolutionary dynamics of multi-agent learning: A survey","author":"bloembergen","year":"2015","journal-title":"Artificial Intelligence"},{"key":"ref21","author":"jaderberg","year":"2016","journal-title":"Reinforcement learning with unsupervised auxiliary tasks"}],"event":{"name":"2017 IEEE 15th International Conference on Industrial Informatics (INDIN)","location":"Emden","start":{"date-parts":[[2017,7,24]]},"end":{"date-parts":[[2017,7,26]]}},"container-title":["2017 IEEE 15th International Conference on Industrial Informatics (INDIN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8095148\/8104734\/08104770.pdf?arnumber=8104770","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,6]],"date-time":"2019-10-06T20:24:25Z","timestamp":1570393465000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8104770\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/indin.2017.8104770","relation":{},"subject":[],"published":{"date-parts":[[2017,7]]}}}