{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:16:42Z","timestamp":1765520202722,"version":"3.48.0"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246873","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"5649-5656","source":"Crossref","is-referenced-by-count":0,"title":["LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robots"],"prefix":"10.1109","author":[{"given":"Peilin","family":"Wu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China"}]},{"given":"Weiji","family":"Xie","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China"}]},{"given":"Jiahang","family":"Cao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China"}]},{"given":"Hang","family":"Lai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China"}]},{"given":"Weinan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"Makoviychuk","year":"2021","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"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.abc5986"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560837"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/4235.585893"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1996.8.7.1341"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.056"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812166"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610485"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1176\/appi.books.9781585622665.33114"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.011"},{"key":"ref16","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29658"},{"article-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"article-title":"Representation learning with contrastive predictive coding","year":"2019","author":"van den Oord","key":"ref20"},{"key":"ref21","first-page":"35603","article-title":"Contrastive learning as goal-conditioned reinforcement learning","volume":"35","author":"Eysenbach","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2916887"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3031549"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800101"},{"article-title":"Foundation policies with hilbert representations","year":"2024","author":"Park","key":"ref27"},{"key":"ref28","first-page":"9870","article-title":"Decoupling representation learning from reinforcement learning","volume-title":"International conference on machine learning","author":"Stooke"},{"article-title":"R3m: A universal visual representation for robot manipulation","year":"2022","author":"Nair","key":"ref29"},{"article-title":"Unsupervised zero-shot reinforcement learning via functional reward encodings","volume-title":"Forty-first International Conference on Machine Learning","author":"Frans","key":"ref30"},{"article-title":"Vip: Towards universal visual reward and representation via value-implicit pretraining","year":"2022","author":"Ma","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989250"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801637"},{"key":"ref34","first-page":"22","article-title":"Walk these ways: Tuning robot control for generalization with multiplicity of behavior","volume-title":"Conference on Robot Learning","author":"Margolis"},{"article-title":"Learning multiple gaits within latent space for quadruped robots","year":"2023","author":"Wu","key":"ref35"},{"key":"ref36","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"Ng","year":"1999","journal-title":"Icml"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"},{"key":"ref38","article-title":"A definition of continual reinforcement learning","volume":"36","author":"Abel","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11595"},{"article-title":"Continual reinforcement learning with multi-timescale replay","year":"2020","author":"Kaplanis","key":"ref40"},{"article-title":"Reset & distill: A recipe for overcoming negative transfer in continual reinforcement learning","year":"2024","author":"Ahn","key":"ref41"},{"key":"ref42","first-page":"6304","article-title":"Disentangling transfer in continual reinforcement learning","volume":"35","author":"Wolczyk","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"International Conference on Learning Representations","author":"Hafner","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161144"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3290509"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981973"},{"key":"ref48","article-title":"A recurrent latent variable model for sequential data","volume":"28","author":"Chung","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2314"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530110"},{"key":"ref52","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"Legged locomotion in challenging terrains using egocentric vision","volume-title":"6th Annual Conference on Robot Learning","author":"Agarwal","key":"ref53"},{"article-title":"Bridging the sim-to-real gap from the information bottleneck perspective","volume-title":"8th Annual Conference on Robot Learning","author":"He","key":"ref54"},{"year":"2022","key":"ref55","article-title":"Unitree robotics"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246873.pdf?arnumber=11246873","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:13:47Z","timestamp":1765520027000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246873\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246873","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}