{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T04:44:44Z","timestamp":1761281084886,"version":"build-2065373602"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100019033","name":"Key Research and Development Program of Shandong Province","doi-asserted-by":"publisher","award":["2025CXGC010111","2025CXGC010210","2024CXGC010212"],"award-info":[{"award-number":["2025CXGC010111","2025CXGC010210","2024CXGC010212"]}],"id":[{"id":"10.13039\/501100019033","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2057"],"award-info":[{"award-number":["U22A2057"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2025.3612147","type":"journal-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T17:39:41Z","timestamp":1758303581000},"page":"22112-22123","source":"Crossref","is-referenced-by-count":0,"title":["A Generalist Agent Learning Architecture for Versatile Quadruped Locomotion"],"prefix":"10.1109","volume":"22","author":[{"given":"Yanyun","family":"Chen","sequence":"first","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}]},{"given":"Ran","family":"Song","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}]},{"given":"Jiapeng","family":"Sheng","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}]},{"given":"Xing","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}]},{"given":"Wenhao","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5906-5074","authenticated-orcid":false,"given":"Yibin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4960-3190","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abb2174"},{"key":"ref3","first-page":"773","article-title":"Fast and efficient locomotion via learned gait transitions","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Yang"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3172469"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2022.3170548"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593885"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2794620"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594448"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793865"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3177289"},{"key":"ref13","article-title":"Robust recovery controller for a quadrupedal robot using deep reinforcement learning","author":"Lee","year":"2019","journal-title":"arXiv:1901.07517"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00444-0"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref16","article-title":"Robot parkour learning","author":"Zhuang","year":"2023","journal-title":"arXiv:2309.05665"},{"key":"ref17","article-title":"A generalist agent","author":"Reed","year":"2022","journal-title":"arXiv:2205.06175"},{"key":"ref18","article-title":"VAE-loco: Versatile quadruped locomotion by learning a disentangled gait representation","author":"Mitchell","year":"2022","journal-title":"arXiv:2205.01179"},{"key":"ref19","first-page":"4455","article-title":"One policy to control them all: Shared modular policies for agent-agnostic control","volume-title":"Proc. ICML","author":"Huang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"article-title":"Multi-critic actor learning: Teaching RL policies to act with style","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Mysore","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.064"},{"key":"ref24","first-page":"22","article-title":"Walk these ways: Tuning robot control for generalization with multiplicity of behavior","volume-title":"Proc. Conf. Robot Learn.","author":"Margolis"},{"key":"ref25","article-title":"DiGrad: Multi-task reinforcement learning with shared actions","author":"Dewangan","year":"2018","journal-title":"arXiv:1802.10463"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(97)00018-3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2003.1241893"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/BIOROB.2008.4762878"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WCICA.2011.5970700"},{"key":"ref30","article-title":"Highly dynamic quadruped locomotion via whole-body impulse control and model predictive control","author":"Kim","year":"2019","journal-title":"arXiv:1909.06586"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref32","first-page":"916","article-title":"Policies modulating trajectory generators","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"I\u00b8s\u00e7en"},{"key":"ref33","article-title":"Learning a contact-adaptive controller for robust, efficient legged locomotion","author":"Da","year":"2020","journal-title":"arXiv:2009.10019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3218167"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3418310"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610151"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO55434.2022.10011737"},{"key":"ref38","article-title":"Imitate and repurpose: Learning reusable robot movement skills from human and animal behaviors","author":"Bohez","year":"2022","journal-title":"arXiv:2203.17138"},{"key":"ref39","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1152\/jn.2001.86.1.447"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1152\/jn.00216.2005"},{"article-title":"What matters for on-policy deep actor-critic methods? A large-scale study","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Andrychowicz","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CoG52621.2021.9619008"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref45","first-page":"20","article-title":"Design overview of the hydraulic quadruped robots","volume-title":"Proc. 14th Scandin. Int. Conf. Fluid power (SICFP)","author":"Semini"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/11173608.pdf?arnumber=11173608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T04:40:34Z","timestamp":1761280834000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11173608\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3612147","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"type":"print","value":"1545-5955"},{"type":"electronic","value":"1558-3783"}],"subject":[],"published":{"date-parts":[[2025]]}}}