{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:41:18Z","timestamp":1769636478854,"version":"3.49.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9197175","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T17:25:46Z","timestamp":1600190746000},"page":"8746-8752","source":"Crossref","is-referenced-by-count":33,"title":["Hybrid Zero Dynamics Inspired Feedback Control Policy Design for 3D Bipedal Locomotion using Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Guillermo A.","family":"Castillo","sequence":"first","affiliation":[]},{"given":"Bowen","family":"Weng","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Ayonga","family":"Hereid","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref32","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014"},{"key":"ref31","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"41:1","DOI":"10.1145\/3072959.3073602","article-title":"Deeploco: Dynamic locomotion skills using hierarchical deep reinforcement learning","volume":"36","author":"peng","year":"2017","journal-title":"ACM Trans Graph"},{"key":"ref34","article-title":"Simulation results for Cassie in MuJoCo","year":"0"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353843"},{"key":"ref11","author":"westervelt","year":"2007","journal-title":"Feedback Control of Dynamic Bipedal Robot Locomotion"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2299342"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2003.1234651"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910379882"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574715000995"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2783371"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1115\/DSCC2015-9899"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-43089-4_26"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814833"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2582731"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2008.2002312"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2461328.2461334"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843605000466"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2006.321385"},{"key":"ref29","article-title":"A simulation library for agility robotics’ cassie robot using mujoco","year":"0"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5648837"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487270"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912452762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2001.973365"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2013.7029990"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.04.021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919859425"},{"key":"ref22","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref21","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793627"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-94042-7_7"},{"key":"ref26","article-title":"Iterative Reinforcement Learning Based Design of Dynamic Locomotion Skills for Cassie","author":"xie","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593722"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09197175.pdf?arnumber=9197175","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:19:56Z","timestamp":1656361196000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197175\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9197175","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}