{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T14:02:37Z","timestamp":1756994557707,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icra.2019.8793627","type":"proceedings-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T01:26:12Z","timestamp":1565659572000},"page":"284-290","source":"Crossref","is-referenced-by-count":11,"title":["Reinforcement Learning Meets Hybrid Zero Dynamics: A Case Study for RABBIT"],"prefix":"10.1109","author":[{"given":"Guillermo A.","family":"Castillo","sequence":"first","affiliation":[]},{"given":"Bowen","family":"Weng","sequence":"additional","affiliation":[]},{"given":"Ayonga","family":"Hereid","sequence":"additional","affiliation":[]},{"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.0030134"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/S1006-1266(07)60009-1"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(89)90094-0"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1988.194594"},{"key":"ref37","article-title":"Robust Adversarial Reinforcement Learning","author":"pinto","year":"2017","journal-title":"ArXiv e-prints"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202230"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TRA.2003.814514"},{"key":"ref34","article-title":"OpenAI Gym","author":"brockman","year":"2016","journal-title":"ArXiv e-prints"},{"journal-title":"Feedback Control of Dynamic Bipedal Robot Locomotion","year":"2007","author":"westervelt","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2783371"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1109\/MCS.2003.1234651","article-title":"Rabbit: a testbed for advanced control theory","volume":"23","author":"chevallereau","year":"2003","journal-title":"IEEE Control Systems Magazine"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1109\/TRO.2008.2010366","article-title":"Asymptotically stable walking of a five-link under actuated 3-d bipedal robot","volume":"25","author":"chevallereau","year":"2009","journal-title":"IEEE Transactions on Robotics"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910379882"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2562059.2562143"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(97)00043-2"},{"key":"ref17","article-title":"Continuous control with deep reinforcement learning","volume":"abs 1509 2971","author":"lillicrap","year":"2015","journal-title":"CoRR"},{"key":"ref18","article-title":"High-dimensional continuous control using generalized advantage estimation","volume":"abs 1506 2438","author":"schulman","year":"2015","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2582731"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073602"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5648837"},{"key":"ref27","first-page":"17","article-title":"Guided policy search","volume":"28","author":"levine","year":"2013","journal-title":"Proceedings of the 30th International Conference on Machine Learning ser Proceedings of Machine Learning Research"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2008.2002312"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912452762"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593722"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2006.321385"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2013.7029990"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487270"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843605000466"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353843"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/70.149940"},{"key":"ref20","article-title":"Combining Trajectory Optimization, Supervised Machine Learning, and Model Structure for Mitigating the Curse of Dimensionality in the Control of Bipedal Robots","author":"da","year":"2017","journal-title":"ArXiv e-prints"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2461328.2461334"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref24","article-title":"Proximal Policy Optimization Algorithms","author":"schulman","year":"2017","journal-title":"ArXiv e-prints"},{"key":"ref23","article-title":"Playing Atari with Deep Reinforcement Learning","author":"mnih","year":"2013","journal-title":"ArXiv e-prints"},{"key":"ref26","article-title":"High dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv preprint arXiv 1506 02349"},{"key":"ref25","first-page":"383","article-title":"Evolving modular fast-weight networks for control","author":"gomez","year":"2005","journal-title":"Artificial Neural Networks Formal Models and Their Applications – ICANN 2005"}],"event":{"name":"2019 International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2019,5,20]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2019,5,24]]}},"container-title":["2019 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8780387\/8793254\/08793627.pdf?arnumber=8793627","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:08:43Z","timestamp":1657854523000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8793627\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8793627","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}