{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T16:26:05Z","timestamp":1776529565427,"version":"3.51.2"},"reference-count":41,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611560","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"5724-5730","source":"Crossref","is-referenced-by-count":3,"title":["An Efficient Model-Based Approach on Learning Agile Motor Skills without Reinforcement"],"prefix":"10.1109","author":[{"given":"Haojie","family":"Shi","sequence":"first","affiliation":[{"name":"Tencent Robotics X,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tingguang","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent Robotics X,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingxu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tencent Robotics X,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiapeng","family":"Sheng","sequence":"additional","affiliation":[{"name":"Tencent Robotics X,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Han","sequence":"additional","affiliation":[{"name":"Tencent Robotics X,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Max Q.-H.","family":"Meng","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology,Shenzhen Key Laboratory of Robotics Perception and Intelligence,Department of Electronic and Electrical Engineering,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"883","article-title":"Learning a contact-adaptive controller for robust, efficient legged locomotion","volume-title":"Conference on Robot Learning","author":"Da"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref3","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":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abb2174"},{"key":"ref5","first-page":"773","article-title":"Fast and efficient locomotion via learned gait transitions","volume-title":"Conference on Robot Learning","author":"Yang"},{"key":"ref6","article-title":"Terrain-aware quadrupedal locomotion via reinforcement learning","author":"Shi","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.064"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342271"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981973"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3618397"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00861-3"},{"key":"ref13","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning","author":"Schulman"},{"key":"ref14","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref15","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560837"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812166"},{"key":"ref19","first-page":"2226","article-title":"Day-dreamer: World models for physical robot learning","volume-title":"Conference on Robot Learning","author":"Wu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555434"},{"key":"ref21","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206174"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593885"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2852785"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2923967"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594448"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460731"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2862902"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2779821"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2798285"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145495"},{"key":"ref34","first-page":"416","article-title":"Real-world robot learning with masked visual pre-training","volume-title":"Conference on Robot Learning","author":"Radosavovic"},{"key":"ref35","article-title":"Algorithmic framework for model-based deep reinforcement learning with theoretical guarantees","author":"Luo","year":"2018"},{"key":"ref36","article-title":"Model-based reinforcement learning via meta-policy optimization","volume-title":"Conference on Robot Learning","author":"Clavera"},{"key":"ref37","article-title":"Model-ensemble trust-region policy optimization","author":"Kurutach","year":"2018"},{"key":"ref38","article-title":"Mastering atari with discrete world models","author":"Hafner","year":"2020"},{"key":"ref39","article-title":"Dream to control: Learning behaviors by latent imagination","author":"Hafner","year":"2019"},{"key":"ref40","article-title":"Mastering diverse domains through world models","author":"Hafner","year":"2023"},{"key":"ref41","volume-title":"Implementation of the pure pursuit path tracking algorithm","author":"Coulter","year":"1992"}],"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\/10611560.pdf?arnumber=10611560","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:18:57Z","timestamp":1723349937000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611560\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611560","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}