{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:11:09Z","timestamp":1777651869238,"version":"3.51.4"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001807","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076161"],"award-info":[{"award-number":["62076161"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10161034","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"7250-7257","source":"Crossref","is-referenced-by-count":10,"title":["Multi-embodiment Legged Robot Control as a Sequence Modeling Problem"],"prefix":"10.1109","author":[{"given":"Chen","family":"Yu","sequence":"first","affiliation":[{"name":"School of Info. Sci. and Tech., ShanghaiTech University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weinan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Lai","sequence":"additional","affiliation":[{"name":"Digital Brain Lab,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Creativity and Art, ShanghaiTech University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laurent","family":"Kneip","sequence":"additional","affiliation":[{"name":"School of Info. Sci. and Tech., ShanghaiTech University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[{"name":"Digital Brain Lab,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/ARTL_a_00207"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/ARTL_a_00228"},{"key":"ref56","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"makoviychuk","year":"20","journal-title":"ArXiv Preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3449726.3463156"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145495"},{"key":"ref14","author":"le goff","year":"2022","journal-title":"Morpho-evolution with learning using a controller archive as an inheritance mechanism"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1002\/0470049715"},{"key":"ref53","article-title":"Layer normalization","author":"ba","year":"20","journal-title":"ArXiv Preprint"},{"key":"ref52","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","volume":"32","author":"kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0186107"},{"key":"ref55","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","author":"rudin","year":"2022","journal-title":"Conference on Robot Learning"},{"key":"ref10","first-page":"125","article-title":"Real-world evolution adapts robot morphology and control to hard-ware limitations","author":"nygaard","year":"0","journal-title":"Proceedings of the Genetic and Evolutionary Computation Conference"},{"key":"ref54","author":"radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417831"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561818"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2019.00009"},{"key":"ref18","first-page":"854","article-title":"Data-efficient co-adaptation of morphology and behaviour with deep reinforcement learning","author":"luck","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref51","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","author":"fujimoto","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref50","article-title":"Tree-based batch mode rein-forcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1249"},{"key":"ref45","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref47","article-title":"Generating wikipedia by summarizing long sequences","author":"liu","year":"20","journal-title":"ArXiv Preprint"},{"key":"ref42","first-page":"1977","article-title":"Speech understanding systems: A summary of results of the five-year research effort at carnegie mellon university","author":"reddy","year":"0","journal-title":"Pittsburgh"},{"key":"ref41","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"janner","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref44","article-title":"Practical bayesian optimization of machine learning algorithms","volume":"25","author":"snoek","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793865"},{"key":"ref49","first-page":"8844","article-title":"Track-former: Multi-object tracking with transformers","author":"meinhardt","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/evco_a_00291"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00320-3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3377929.3398095"},{"key":"ref4","article-title":"Learning to walk in the real world with minimal human effort","author":"ha","year":"20","journal-title":"ArXiv Preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3192798"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2021.696452"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2019.00071"},{"key":"ref40","article-title":"Online decision transformer","author":"zheng","year":"20","journal-title":"ArXiv Preprint"},{"key":"ref35","article-title":"Genloco: Generalized locomotion controllers for quadrupedal robots","author":"feng","year":"20","journal-title":"ArXiv Preprint"},{"key":"ref34","article-title":"Nervenet: Learning structured policy with graph neural networks","author":"wang","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref37","article-title":"A generalist agent","author":"reed","year":"20","journal-title":"ArXiv Preprint"},{"key":"ref36","article-title":"Training agents using upside-down reinforcement learning","author":"srivastava","year":"20","journal-title":"ArXiv Preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793537"},{"key":"ref30","article-title":"Hardware conditioned policies for multi-robot transfer learning","volume":"31","author":"chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref33","article-title":"Learning to control self-assembling morphologies: a study of generalization via modularity","volume":"32","author":"pathak","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref32","first-page":"4455","article-title":"One policy to control them all: Shared modular policies for agent-agnostic control","author":"huang","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812166"},{"key":"ref1","author":"raff","year":"2012","journal-title":"The Shape of Life Genes Development and the Evolution of Animal Form"},{"key":"ref39","article-title":"Can wikipedia help offline reinforcement learning?","author":"reid","year":"20","journal-title":"ArXiv Preprint"},{"key":"ref38","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968251"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3128697"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152681"},{"key":"ref25","article-title":"System identification and modeling for mabel, a bipedal robot with a cable-differential-based compliant drivetrain","volume":"6","author":"park","year":"0","journal-title":"Dynamic Walking Conference (DW) MIT"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25874-z"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594448"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919840426"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.061"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","location":"London, United Kingdom","start":{"date-parts":[[2023,5,29]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10161034.pdf?arnumber=10161034","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:36:39Z","timestamp":1690220199000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10161034\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10161034","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}