{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T03:35:05Z","timestamp":1778902505625,"version":"3.51.4"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10342187","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"7531-7538","source":"Crossref","is-referenced-by-count":9,"title":["End-to-End Reinforcement Learning for Torque Based Variable Height Hopping"],"prefix":"10.1109","author":[{"given":"Raghav","family":"Soni","sequence":"first","affiliation":[{"name":"Indian Institute of Technology (Banaras Hindu University),Department of Electronics Engineering,Varanasi,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Harnack","sequence":"additional","affiliation":[{"name":"DFKI GmbH Robotic-s Innovation Center,Bremen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hannah","family":"Isermann","sequence":"additional","affiliation":[{"name":"DFKI GmbH Robotic-s Innovation Center,Bremen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sotaro","family":"Fushimi","sequence":"additional","affiliation":[{"name":"Kyoto University,Undergraduate Course Program of Mechanical and Systems Engineering,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shivesh","family":"Kumar","sequence":"additional","affiliation":[{"name":"DFKI GmbH Robotic-s Innovation Center,Bremen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank","family":"Kirchner","sequence":"additional","affiliation":[{"name":"DFKI GmbH Robotic-s Innovation Center,Bremen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2008.4756020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2006.1641857"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487279"},{"key":"ref4","article-title":"Learning torque control for quadrupedal locomotion","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560769"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967913"},{"key":"ref8","first-page":"317","article-title":"Learning locomotion skills for cassie: Iterative design and sim-to-real","volume-title":"Conference on Robot Learning","author":"Xie","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-04606-3"},{"key":"ref11","article-title":"Robust quadruped jumping via deep reinforcement learning","author":"Bellegarda","year":"2020","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/027836498400300207"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1984.6313238"},{"key":"ref14","volume-title":"Uniroo-a one legged dynamic hopping robot","author":"Zeglin","year":"1991"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014359"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1993.325684"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1088\/1748-3190\/ab6ed8"},{"key":"ref18","article-title":"Hoppy: an open-source and low-cost kit for dynamic robotics education","author":"Ramos","year":"2020","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492900002919"},{"key":"ref20","article-title":"The expressive power of neural networks: A view from the width","volume":"30","author":"Lu","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CYBER.2018.8688117"},{"key":"ref22","article-title":"Model-free reinforcement learning for robust locomotion using trajectory optimization for exploration","author":"Bogdanovic","year":"2021","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/nrn3112"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341260"},{"key":"ref25","volume-title":"qdd100 beta 3 servo","year":"2022"},{"key":"ref26","volume-title":"Underactuated Robotics","author":"Tedrake","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/095965180321700203"},{"key":"ref28","volume-title":"Software and control design for the mit cheetah quadruped robots","author":"Di Carlo","year":"2020"},{"key":"ref29","volume-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","author":"Coumans","year":"2016"},{"key":"ref30","volume-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"ref31","article-title":"Generalized state-dependent exploration for deep reinforcement learning in robotics","author":"Raffin","year":"2020","journal-title":"Arxiv"},{"key":"ref32","author":"Brockman","year":"2016","journal-title":"Openai gym"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref34","volume-title":"Comparing popular simulation environments in the scope of robotics and reinforcement learning","author":"K\u00f6rber","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/106365601750190398"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.011"},{"key":"ref38","article-title":"RealAIGym: Education and Research Platform for Studying Athletic Intelligence","volume-title":"Proceedings of Robotics Science and Systems Work-shop Mind the Gap: Opportunities and Challenges in the Transition Between Research and Industry","author":"Wiebe"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03884"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/mra.2023.3341257"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3269296"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10342187.pdf?arnumber=10342187","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T19:39:10Z","timestamp":1731008350000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342187\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342187","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}