{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:26:21Z","timestamp":1780763181755,"version":"3.54.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001659","name":"German Research Foundation","doi-asserted-by":"publisher","award":["BE 2556\/16-2"],"award-info":[{"award-number":["BE 2556\/16-2"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9812023","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"2671-2677","source":"Crossref","is-referenced-by-count":11,"title":["Real-Robot Deep Reinforcement Learning: Improving Trajectory Tracking of Flexible-Joint Manipulator with Reference Correction"],"prefix":"10.1109","author":[{"given":"Dmytro","family":"Pavlichenko","sequence":"first","affiliation":[{"name":"University of Bonn,Autonomous Intelligent Systems (AIS) Group, Computer Science Institute VI,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sven","family":"Behnke","sequence":"additional","affiliation":[{"name":"University of Bonn,Autonomous Intelligent Systems (AIS) Group, Computer Science Institute VI,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IRC52146.2021.00008"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2017.8246876"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363544"},{"key":"ref30","article-title":"Revisiting fundamentals of experience replay","author":"fedus","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2006.1636313"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389553"},{"key":"ref12","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume":"80","author":"haarnoja","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref13","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"schulman","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref14","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref15","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume":"48","author":"mnih","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref16","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref17","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","author":"haarnoja","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2012.2189004"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/app11104685"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_39"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2870642"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560769"},{"key":"ref29","first-page":"834","article-title":"Improving stochastic policy gradients in continuous control with deep reinforcement learning using the beta distribution","author":"chou","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref5","article-title":"DeepWalk: Omnidirectional bipedal gait by deep reinforcement learning","author":"diego","year":"0","journal-title":"IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref8","author":"an","year":"1988","journal-title":"Model-Based Control of a Robot Manipulator"},{"key":"ref7","author":"haarnoja","year":"2018","journal-title":"Soft actor-critic algorithms and applications"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2012.07.014"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/002071700405905"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/acs.4480040610"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3182\/20140824-6-ZA-1003.02511"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2018.11.006"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01079"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197134"},{"key":"ref26","author":"kumar","year":"2021","journal-title":"Joint space control via deep reinforcement learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/app9020348"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09812023.pdf?arnumber=9812023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:09:00Z","timestamp":1667516940000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9812023\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9812023","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}