{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T03:12:09Z","timestamp":1776913929766,"version":"3.51.2"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127792","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"11683-11690","source":"Crossref","is-referenced-by-count":3,"title":["Composing Dextrous Grasping and In-Hand Manipulation via Scoring with a Reinforcement Learning Critic"],"prefix":"10.1109","author":[{"given":"Lennart","family":"R\u00f6stel","sequence":"first","affiliation":[{"name":"Technical University of Munich (aidx-lab.org), and the DLR Institute of Robotics & Mechatronics (German Aerospace Center),Learning AI for Dextrous Robots Lab"}]},{"given":"Dominik","family":"Winkelbauer","sequence":"additional","affiliation":[{"name":"Technical University of Munich (aidx-lab.org), and the DLR Institute of Robotics & Mechatronics (German Aerospace Center),Learning AI for Dextrous Robots Lab"}]},{"given":"Johannes","family":"Pitz","sequence":"additional","affiliation":[{"name":"Technical University of Munich (aidx-lab.org), and the DLR Institute of Robotics & Mechatronics (German Aerospace Center),Learning AI for Dextrous Robots Lab"}]},{"given":"Leon","family":"Sievers","sequence":"additional","affiliation":[{"name":"Technical University of Munich (aidx-lab.org), and the DLR Institute of Robotics & Mechatronics (German Aerospace Center),Learning AI for Dextrous Robots Lab"}]},{"given":"Berthold","family":"B\u00e4uml","sequence":"additional","affiliation":[{"name":"Technical University of Munich (aidx-lab.org), and the DLR Institute of Robotics & Mechatronics (German Aerospace Center),Learning AI for Dextrous Robots Lab"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981133"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812093"},{"key":"ref3","article-title":"Learning dexterous In-Hand manipulation","year":"2018","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"A system for general in-hand object re-orientation","volume-title":"Conference on Robot Learning","author":"Chen","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160756"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2001.932538"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1987.1088014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/56.769"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/100216.100261"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1992.219918"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1308797"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0156"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914549607"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354004"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139793"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811756"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3140424"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-014-9402-3"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/027836498200100102"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/027836498700600206"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/027836498500400201"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/70.768187"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2011.07.014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2011.6181509"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844067"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399090"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145961"},{"key":"ref28","article-title":"In-Hand object rotation via rapid motor adaptation","volume-title":"Proc. Conference on Robot Learning","author":"Qi"},{"key":"ref29","article-title":"Sampling-based exploration for re-inforcement learning of dexterous manipulation","author":"Khandate","journal-title":"arXiv preprint, 2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids57100.2023.10375194"},{"key":"ref31","article-title":"Solving rubik\u2019s cube with a robot hand","journal-title":"arXiv preprint, 2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160216"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-024-10170-8"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adc9244"},{"key":"ref35","article-title":"General In-Hand object rotation with vision and touch","volume-title":"Proc. Conference on Robot Learning","author":"Qi"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610532"},{"key":"ref37","article-title":"Lessons from learning to spin\u201cpens\u201d","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802864"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225104"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids57100.2023.10375210"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981730"},{"key":"ref42","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Omniverse isaac gym reinforcement learning environments for isaac sim","year":"2023"},{"key":"ref44","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","journal-title":"arXiv [cs.LG], 2015"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids53995.2022.10000184"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids57100.2023.10375208"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907220"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6697103"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152473"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/34.121791"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981717"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127792.pdf?arnumber=11127792","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:05:53Z","timestamp":1756879553000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127792\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127792","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}