{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T17:13:39Z","timestamp":1776446019318,"version":"3.51.2"},"reference-count":63,"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\/icra57147.2024.10610485","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"10829-10836","source":"Crossref","is-referenced-by-count":13,"title":["Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion"],"prefix":"10.1109","author":[{"given":"Laura","family":"Smith","sequence":"first","affiliation":[{"name":"Berkeley AI Research, UC Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunhao","family":"Cao","sequence":"additional","affiliation":[{"name":"Berkeley AI Research, UC Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergey","family":"Levine","sequence":"additional","affiliation":[{"name":"Berkeley AI Research, UC Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume":"abs\/2004.12570","author":"Zhu","year":"2020","journal-title":"The ingredients of real-world robotic reinforcement learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307456"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"ref5","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Conference on Robot Learning (CoRL)","volume":"abs\/1806.10293","author":"Kalashnikov"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref7","volume":"abs\/2104.08212","author":"Kalashnikov","year":"2021","journal-title":"Mt-opt: Continuous multi-task robotic reinforcement learning at scale"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.063"},{"key":"ref9","article-title":"Solar: Deep structured representations for model-based reinforcement learning","volume-title":"International Conference on Machine Learning (ICML)","author":"Zhang"},{"key":"ref10","article-title":"Deep dynamics models for learning dexterous manipulation","volume-title":"Conference on Robot Learning (CoRL)","volume":"abs\/1909.11652","author":"Nagabandi"},{"key":"ref11","article-title":"The primacy bias in deep reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Nikishin"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509805"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2794620"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2014.7041375"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9479-3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7758092"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593885"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793865"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917694244"},{"key":"ref20","first-page":"1154","article-title":"Representation-free model predictive control for dynamic motions in quadrupeds","volume-title":"IEEE Transactions on Robotics","volume":"37","author":"Ding","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759424"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref23","volume":"abs\/1810.02422","author":"He","year":"2018","journal-title":"Zero-shot skill composition and simulation-to-real transfer by learning task representations"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968053"},{"key":"ref25","article-title":"Policies modulating trajectory generators","volume-title":"Conference on Robot Learning (CoRL)","volume":"abs\/1910.02812","author":"Iscen"},{"key":"ref26","article-title":"Learning locomotion skills for cassie: Iterative design and sim-to-real","volume-title":"Conference on Robot Learning (CoRL)","author":"Xie"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.064"},{"key":"ref30","volume":"abs\/2104.04644","author":"Yang","year":"2021","journal-title":"Fast and efficient locomotion via learned gait transitions"},{"key":"ref31","volume":"abs\/2109.11978","author":"Rudin","year":"2021","journal-title":"Learning to walk in minutes using massively parallel deep reinforcement learning"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.011"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3084374"},{"key":"ref35","article-title":"Learning to jump from pixels","volume-title":"Conference on Robot Learning","author":"Margolis"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3191071"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160751"},{"key":"ref38","volume-title":"Opt-mimic: Imit@articleAchiam2017ConstrainedPO, title=Constrained Policy Optimization, author=Joshua Achiam and David Held and Aviv Tamar and P. Abbeel, journal=ArXiv, year=2017, volume=abs\/1705.10528, url=https:\/\/api.semanticscholar.org\/CorpusID:10647707 ation of optimized trajectories for dynamic quadruped behaviors","volume":"abs\/2210.01247","author":"Fuchioka","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.051"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389841"},{"key":"ref41","article-title":"Learning cpg sensory feedback with policy gradient for biped locomotion for a full-body humanoid","volume-title":"AAAI","author":"Endo"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.075"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794207"},{"key":"ref44","article-title":"Data efficient reinforcement learning for legged robots","volume-title":"Conference on Robot Learning (CoRL)","volume":"abs\/1907.03613","author":"Yang"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1176\/appi.books.9781585622665.33114"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.056"},{"key":"ref47","volume":"abs\/2002.08550","author":"Ha","year":"2020","journal-title":"Learning to walk in the real world with minimal human effort"},{"key":"ref48","article-title":"Sample-efficient reinforcement learning by breaking the replay ratio barrier","volume-title":"International Conference on Learning Representations","author":"D\u2019Oro"},{"key":"ref49","article-title":"JAX: composable transformations of Python+NumPy programs","author":"Bradbury","year":"2018"},{"key":"ref50","article-title":"MuJoCo Menagerie: A collection of high-quality simulation models for MuJoCo","author":"Zakka","year":"2022"},{"key":"ref51","volume-title":"When to trust your model: Model-based policy optimization","volume":"abs\/1906.08253","author":"Janner","year":"2019"},{"key":"ref52","article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hafner"},{"key":"ref53","volume-title":"Regularization matters in policy optimization - an empirical study on continuous control","author":"Liu","year":"2020"},{"key":"ref54","article-title":"Dropout q-functions for doubly efficient reinforcement learning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hiraoka"},{"key":"ref55","volume-title":"Sunrise: A simple unified framework for ensemble learning in deep reinforcement learning","volume":"abs\/2007.04938","author":"Lee","year":"2020"},{"key":"ref56","volume":"abs\/2101.05982","author":"Chen","year":"2021","journal-title":"Randomized ensembled double q-learning: Learning fast without a model"},{"key":"ref57","volume-title":"Efficient deep reinforcement learning requires regulating overfitting","volume":"abs\/2304.10466","author":"Li","year":"2023"},{"key":"ref58","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref59","volume":"abs\/1607.06450","author":"Ba","year":"2016","journal-title":"Layer normalization"},{"key":"ref60","article-title":"Minimizing energy consumption leads to the emergence of gaits in legged robots","volume-title":"Conference on Robot Learning (CoRL)","author":"Fu"},{"key":"ref61","volume-title":"Learning agile soccer skills for a bipedal robot with deep reinforcement learning","volume":"abs\/2304.13653","author":"Haarnoja","year":"2023"},{"key":"ref62","article-title":"Minimizing energy consumption leads to the emergence of gaits in legged robots","volume-title":"Conference on Robot Learning (CoRL)","author":"Fu"},{"key":"ref63","article-title":"Model-based active exploration","volume-title":"International Conference on Machine Learning","author":"Shyam"}],"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\/10610485.pdf?arnumber=10610485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:49:59Z","timestamp":1723268999000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610485\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610485","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}