{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T17:02:01Z","timestamp":1772557321424,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610705","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"7405-7411","source":"Crossref","is-referenced-by-count":7,"title":["Human-Robot Gym: Benchmarking Reinforcement Learning in Human-Robot Collaboration"],"prefix":"10.1109","author":[{"given":"Jakob","family":"Thumm","sequence":"first","affiliation":[{"name":"Technical University of Munich,Department of Computer Engineering,Germany"}]},{"given":"Felix","family":"Trost","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Department of Computer Engineering,Germany"}]},{"given":"Matthias","family":"Althoff","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Department of Computer Engineering,Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/robotics10010022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2022.102432"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197411"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/iros47612.2022.9982244"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811698"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"issue":"268","key":"ref8","first-page":"1","article-title":"Stable-Baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989334"},{"key":"ref10","first-page":"1","article-title":"Towards collaborative robots as intelligent co-workers in human-robot joint tasks: What to do and who does it?","volume-title":"Proc. of the Int. Symp. on Robotics","author":"Cunha"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-016-9556-2"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fnbot.2018.00007","article-title":"Learning semantics of gestural in structions for human-robot collaboration","volume":"12","author":"Shukla","year":"2018","journal-title":"Frontiers in Neurorobotics"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3280752"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-020-01183-3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2017.8324507"},{"key":"ref16","first-page":"189","article-title":"Efficient model learning from joint-action demonstrations for human-robot collaborative tasks","volume-title":"Proc. of the ACM\/IEEE Int. Conf. on Human-Robot Interaction (HRI)","author":"Nikolaidis"},{"key":"ref17","article-title":"robosuite: A modular simulation framework and benchmark for robot learning","author":"Zhu","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3270034"},{"key":"ref19","first-page":"80","article-title":"BEHAVIOR-1K: A benchmark for embodied AI with 1,000 everyday activities and realistic simulation","volume-title":"Proc. of the Conf. on Robot Learning (CoRL)","volume":"205","author":"Li"},{"key":"ref20","first-page":"1094","article-title":"Meta-World: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. of the Conf. on Robot Learning (CoRL)","author":"Yu"},{"key":"ref21","first-page":"1","article-title":"Towards making virtual human-robot interaction a reality","volume-title":"Proc. of the Int. Workshop on Virtual, Augmented, and Mixed-Reality for Human-Robot Interactions (VAM-HRI)","author":"Higgins"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2021.549360"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812302"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10085-1"},{"key":"ref25","first-page":"34 556","article-title":"Jump-start reinforcement learning","volume-title":"Proc. of the Int. Conf. on Machine Learning (ICML)","author":"Uchendu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3213246"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610776"},{"key":"ref29","article-title":"Hydra - a framework for elegantly configuring complex applications","author":"Yadan","year":"2019"},{"key":"ref30","first-page":"5055","article-title":"Hindsight experience replay","volume-title":"Proc. of the Int. Conf. on Neural Information Processing Systems (NeurIPS)","author":"Andrychowicz"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197468"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SII.2019.8700380"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342464"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aaw1924"},{"key":"ref35","article-title":"Robotics - safety requirements - part 1: Industrial robots","volume-title":"Tech. Rep. DIN EN ISO 10218-1:2021-09 DC","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8264632"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636610"},{"key":"ref38","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"ref40","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. of the Int. Conf. on Machine Learning (ICML)","author":"Haarnoja"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610705.pdf?arnumber=10610705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:53:44Z","timestamp":1723269224000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610705\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610705","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}