{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:37:56Z","timestamp":1757608676278,"version":"3.44.0"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0161700"],"award-info":[{"award-number":["2022ZD0161700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176135"],"award-info":[{"award-number":["62176135"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128263","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"15957-15964","source":"Crossref","is-referenced-by-count":0,"title":["Fine-Tuning Hard-to-Simulate Objectives for Quadruped Locomotion: A Case Study on Total Power Saving"],"prefix":"10.1109","author":[{"given":"Ruiqian","family":"Nai","sequence":"first","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiacheng","family":"You","sequence":"additional","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liu","family":"Cao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanchen","family":"Cui","sequence":"additional","affiliation":[{"name":"Shanghai Qi Zhi Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huazhe","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241312698"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asej.2020.11.005"},{"issue":"3","key":"ref3","first-page":"177","article-title":"Anthropomorphism and the social robot","volume-title":"Robotics and Autonomous Systems","volume":"42","author":"Duffy","year":"2003"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/2376.001.0001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-32552-1_54"},{"volume-title":"Unitree gol","key":"ref6"},{"volume-title":"Unitree go2","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793865"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2018.8525795"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152870"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref14","article-title":"Adaptive mobile manipulation for articulated objects in the open world","author":"Xiong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"403","article-title":"Legged locomotion in challenging terrains using egocentric vision","volume-title":"Conference on robot learning. PMLR","author":"Agarwal","year":"2023"},{"key":"ref16","first-page":"22","article-title":"Walk these ways: Tuning robot control for generalization with multiplicity of behavior","volume-title":"Conference on Robot Learning. PMLR","author":"Margolis","year":"2023"},{"key":"ref17","article-title":"Robot parkour learning","author":"Zhuang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231224053"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.064"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981973"},{"journal-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","year":"2021","author":"Makoviychuk","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2776880.2792704"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1201\/9781420009248-13"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IEMDC.2009.5075251"},{"volume-title":"Unitree gol motor","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/en11010120"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10609983"},{"key":"ref29","first-page":"773","article-title":"Fast and efficient locomotion via learned gait transitions","volume-title":"Conference on robot learning. PMLR","author":"Yang","year":"2022"},{"key":"ref30","article-title":"Minimizing energy consumption leads to the emergence of gaits in legged robots","author":"Fu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref31","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Conference on Robot Learning. PMLR","author":"Rudin","year":"2022"},{"volume-title":"Robotsguide: Mini cheetah","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2014.2339013"},{"key":"ref34","article-title":"Learning to walk in the real world with minimal human effort","author":"Ha","year":"2020","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.011"},{"key":"ref36","article-title":"A walk in the park: Learning to walk in 20 minutes with model-free reinforcement learning","author":"Smith","year":"2022","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Grow your limits: Continuous improvement with real-world rl for robotic locomotion","author":"Smith","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812166"},{"key":"ref39","article-title":"Uni-o4: Unifying online and offline deep reinforcement learning with multi-step on-policy optimization","author":"Lei","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611560"},{"key":"ref41","article-title":"Dropout q-functions for doubly efficient reinforcement learning","author":"Hiraoka","year":"2021","journal-title":"arXiv preprint"},{"key":"ref42","first-page":"8655","article-title":"Controlvae: Controllable variational autoencoder","volume-title":"International conference on machine learning. PMLR","author":"Shao","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560935"},{"key":"ref44","first-page":"8661","article-title":"Efficient differentiable simulation of articulated bodies","volume-title":"International Conference on Machine Learning. PMLR","author":"Qiao","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981687"},{"key":"ref46","first-page":"8459","article-title":"Learning to simulate complex physics with graph networks","volume-title":"International conference on machine learning. PMLR","author":"Sanchez-Gonzalez","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593995"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref49","first-page":"212","article-title":"i-sim2real: Reinforcement learning of robotic policies in tight human-robot interaction loops","volume-title":"Conference on Robot Learning. PMLR","author":"Abeyruwan","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adj7246"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3400935"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802334"},{"key":"ref53","article-title":"Multi-task learning as multi-objective optimization","volume":"31","author":"Sener","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1080\/23311916.2018.1502242"},{"key":"ref55","article-title":"Kickstarting deep reinforcement learning","author":"Schmitt","year":"2018","journal-title":"arXiv preprint"},{"key":"ref56","first-page":"16 828","article-title":"The primacy bias in deep reinforcement learning","volume-title":"International conference on machine learning. PMLR","author":"Nikishin","year":"2022"},{"key":"ref57","first-page":"30 365","article-title":"Bigger, better, faster:Human-level atari with human-level efficiency","volume-title":"International Conference on Machine Learning. PMLR","author":"Schwarzer","year":"2023"},{"key":"ref58","article-title":"Reward centering","author":"Naik","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128263.pdf?arnumber=11128263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:11:46Z","timestamp":1756879906000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128263\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128263","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}