{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T01:13:08Z","timestamp":1776301988422,"version":"3.50.1"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10609983","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"11467-11473","source":"Crossref","is-referenced-by-count":6,"title":["Maximizing Quadruped Velocity by Minimizing Energy"],"prefix":"10.1109","author":[{"given":"Srinath","family":"Mahankali","sequence":"first","affiliation":[{"name":"MIT,Improbable AI Lab,Cambridge,USA"}]},{"given":"Chi-Chang","family":"Lee","sequence":"additional","affiliation":[{"name":"Research Center for Information Technology Innovation,Academia Sinica,Taiwan"}]},{"given":"Gabriel B.","family":"Margolis","sequence":"additional","affiliation":[{"name":"MIT,Improbable AI Lab,Cambridge,USA"}]},{"given":"Zhang-Wei","family":"Hong","sequence":"additional","affiliation":[{"name":"MIT,Improbable AI Lab,Cambridge,USA"}]},{"given":"Pulkit","family":"Agrawal","sequence":"additional","affiliation":[{"name":"MIT,Improbable AI Lab,Cambridge,USA"}]}],"member":"263","reference":[{"key":"ref1","author":"Sutton","year":"2018","journal-title":"Reinforcement learning: An introduction"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.011"},{"key":"ref4","article-title":"Learning to jump from pixels","volume-title":"Conference on Robot Learning","author":"Margolis"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160325"},{"key":"ref8","first-page":"297","article-title":"A system for general in-hand object re-orientation","volume-title":"Conference on Robot Learning","author":"Chen"},{"key":"ref9","article-title":"Visual dexterity: In-hand dexterous manipulation from depth","author":"Chen","year":"2022"},{"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","article-title":"Walk these ways: Tuning robot control for generalization with multiplicity of behavior","volume-title":"Conference on Robot Learning","author":"Margolis"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981198"},{"key":"ref14","first-page":"138","article-title":"Deep whole-body control: learning a unified policy for manipulation and locomotion","volume-title":"Conference on Robot Learning","author":"Fu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tro.2024.3400935"},{"key":"ref16","article-title":"Minimizing energy consumption leads to the emergence of gaits in legged robots","volume-title":"Conference on Robot Learning","author":"Fu"},{"key":"ref17","first-page":"773","article-title":"Fast and efficient locomotion via learned gait transitions","volume-title":"Conference on Robot Learning","author":"Yang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/292239a0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1242\/jeb.01498"},{"key":"ref20","article-title":"A generalized algorithm for multi-objective reinforcement learning and policy adaptation","volume":"32","author":"Yang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"4996","article-title":"Redeeming intrinsic rewards via constrained optimization","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","first-page":"31 077","article-title":"TGRL: An algorithm for teacher guided reinforcement learning","volume-title":"Proceedings of the 40th International Conference on Machine Learning","volume":"202","author":"Shenfeld"},{"key":"ref23","article-title":"Exploration by random network distillation","volume-title":"International Conference on Learning Representations","author":"Burda"},{"key":"ref24","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Icml","volume":"99","author":"Ng"},{"key":"ref25","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"Makoviychuk","year":"2021"},{"key":"ref26","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Conference on Robot Learning","author":"Rudin"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2014.2339013"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3151396"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref30","first-page":"29 304","article-title":"Deep reinforcement learning at the edge of the statistical precipice","volume":"34","author":"Agarwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref32","article-title":"Fast and efficient locomotion via learned gait transitions","volume-title":"Conference on Robot Learning","author":"Yang"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459670"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981973"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160562"},{"key":"ref36","article-title":"Evaluation of constrained reinforcement learning algorithms for legged locomotion","author":"Lee","year":"2023"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10609983.pdf?arnumber=10609983","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:17:50Z","timestamp":1723267070000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10609983\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10609983","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}