{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T06:56:32Z","timestamp":1781506592899,"version":"3.54.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/lra.2023.3307008","type":"journal-article","created":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T18:05:46Z","timestamp":1692641146000},"page":"6619-6626","source":"Crossref","is-referenced-by-count":42,"title":["RL + Model-Based Control: Using On-Demand Optimal Control to Learn Versatile Legged Locomotion"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2512-5849","authenticated-orcid":false,"given":"Dongho","family":"Kang","sequence":"first","affiliation":[{"name":"Computational Robotics Lab in the Department of Computer Science, ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9822-3701","authenticated-orcid":false,"given":"Jin","family":"Cheng","sequence":"additional","affiliation":[{"name":"Computational Robotics Lab in the Department of Computer Science, ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8173-8311","authenticated-orcid":false,"given":"Miguel","family":"Zamora","sequence":"additional","affiliation":[{"name":"Computational Robotics Lab in the Department of Computer Science, ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9734-2693","authenticated-orcid":false,"given":"Fatemeh","family":"Zargarbashi","sequence":"additional","affiliation":[{"name":"Computational Robotics Lab in the Department of Computer Science, ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6604-4784","authenticated-orcid":false,"given":"Stelian","family":"Coros","sequence":"additional","affiliation":[{"name":"Computational Robotics Lab in the Department of Computer Science, ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968028"},{"key":"ref35","first-page":"22","article-title":"Walk these ways: Tuning robot control for generalization with multiplicity of behavior","author":"margolis","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2978444"},{"key":"ref34","first-page":"12348","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"raffin","year":"2021","journal-title":"J Mach Learn Res"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206268"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594448"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635838"},{"key":"ref31","article-title":"Unitree robotics","year":"0"},{"key":"ref30","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.3003464"},{"key":"ref33","article-title":"Open dynamics engine","author":"smith","year":"2007"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2798285"},{"key":"ref32","year":"0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref1","article-title":"Optimization-based control for dynamic legged robots","author":"wensing","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793669"},{"key":"ref16","article-title":"Highly dynamic quadruped locomotion via whole-body impulse control and model predictive control","author":"kim","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.064"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref26","article-title":"Reinforcement learning for legged robots: Motion imitation from model-based optimal control","author":"miller","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160562"},{"key":"ref20","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","author":"rudin","year":"0","journal-title":"Proc 5th Conf Robot Learn"},{"key":"ref22","first-page":"916","article-title":"Policies modulating trajectory generators","author":"iscen","year":"0","journal-title":"Proc 2nd Conf Robot Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00576-3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3136645"},{"key":"ref29","article-title":"Optimal control via second order sensitivity analysis","author":"zimmermann","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560855"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341572"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793865"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.ade2256"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981945"},{"key":"ref5","article-title":"Nonlinear model predictive control for quadrupedal locomotion using second-order sensitivity analysis","author":"kang","year":"2022"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10220574\/10225268.pdf?arnumber=10225268","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:35:39Z","timestamp":1699904139000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10225268\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":36,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3307008","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}