{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T00:14:34Z","timestamp":1768004074586,"version":"3.49.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T00:00:00Z","timestamp":1661126400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T00:00:00Z","timestamp":1661126400000},"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":[[2022,8,22]]},"DOI":"10.1109\/mmar55195.2022.9874304","type":"proceedings-article","created":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T20:07:54Z","timestamp":1662667674000},"page":"300-305","source":"Crossref","is-referenced-by-count":8,"title":["Sim2Real Deep Reinforcement Learning of Compliance-based Robotic Assembly Operations"],"prefix":"10.1109","author":[{"given":"Oliver","family":"Petrovic","sequence":"first","affiliation":[{"name":"RWTH Aachen University,Laboratory for Machine Tools and Production Engineering (WZL),Department of Automation and Control Chair of Machine Tools,Aachen,Germany,52074"}]},{"given":"Lukas","family":"Schaper","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Laboratory for Machine Tools and Production Engineering (WZL),Department of Automation and Control Chair of Machine Tools,Aachen,Germany,52074"}]},{"given":"Simon","family":"Roggendorf","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Laboratory for Machine Tools and Production Engineering (WZL),Department of Automation and Control Chair of Machine Tools,Aachen,Germany,52074"}]},{"given":"Simon","family":"Storms","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Laboratory for Machine Tools and Production Engineering (WZL),Department of Automation and Control Chair of Machine Tools,Aachen,Germany,52074"}]},{"given":"Christian","family":"Brecher","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Laboratory for Machine Tools and Production Engineering (WZL),Department of Automation and Control Chair of Machine Tools,Aachen,Germany,52074"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume":"abs 1903 8254","author":"rakelly","year":"2019","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/app10196923"},{"key":"ref12","article-title":"Learning sequences of manipulation primitives for robotic assembly","volume":"abs 2011 778","author":"vuong","year":"2020","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2959445"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341260"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206325"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389727"},{"key":"ref17","author":"smits","year":"0","journal-title":"KDL Kinematics and Dynamics Library"},{"key":"ref18","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume":"80","author":"haarnoja","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref19","article-title":"Soft actor-critic algorithms and applications","volume":"abs 1812 5905","author":"haarnoja","year":"2018","journal-title":"CoRR"},{"key":"ref4","article-title":"Learning continuous control policies by stochastic value gradients","volume":"28","author":"heess","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref3","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341617"},{"key":"ref5","author":"tan","year":"2018","journal-title":"Sim-to-real Learning agile locomotion for quadruped robots"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202244"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340848"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967995"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340956"}],"event":{"name":"2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR)","location":"Mi\u0119dzyzdroje, Poland","start":{"date-parts":[[2022,8,22]]},"end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9873851\/9874261\/09874304.pdf?arnumber=9874304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T21:13:32Z","timestamp":1664226812000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9874304\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,22]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/mmar55195.2022.9874304","relation":{},"subject":[],"published":{"date-parts":[[2022,8,22]]}}}