{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T00:26:20Z","timestamp":1783124780495,"version":"3.54.6"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T00:00:00Z","timestamp":1720137600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T00:00:00Z","timestamp":1720137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Mach Intell"],"DOI":"10.1038\/s42256-024-00861-3","type":"journal-article","created":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T06:01:46Z","timestamp":1720159306000},"page":"787-798","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":56,"title":["Lifelike agility and play in quadrupedal robots using reinforcement learning and generative pre-trained models"],"prefix":"10.1038","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1404-2415","authenticated-orcid":false,"given":"Lei","family":"Han","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6549-3438","authenticated-orcid":false,"given":"Qingxu","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiapeng","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingguang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0488-9869","authenticated-orcid":false,"given":"Yizheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuzhen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5147-2695","authenticated-orcid":false,"given":"Rui","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0737-1416","authenticated-orcid":false,"given":"Wanchao","family":"Chi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonghui","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingzhu","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Teng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6606-2525","authenticated-orcid":false,"given":"Zhengyou","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,5]]},"reference":[{"key":"861_CR1","doi-asserted-by":"crossref","unstructured":"Tan, J. et al. Sim-to-real: learning agile locomotion for quadruped robots. In Proc. Robotics: Science and Systems Vol. XIV (MIT Press Journals, 2018).","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"861_CR2","unstructured":"Haarnoja, T., Hartikainen, K., Abbeel, P. and Levine, S. Latent space policies for hierarchical reinforcement learning. In Proc. 35th International Conference on Machine Learning 1851\u20131860 (PMLR, 2018)."},{"key":"861_CR3","doi-asserted-by":"publisher","first-page":"eaau5872","DOI":"10.1126\/scirobotics.aau5872","volume":"4","author":"J Hwangbo","year":"2019","unstructured":"Hwangbo, J. et al. Learning agile and dynamic motor skills for legged robots. Sci. Rob. 4, eaau5872 (2019).","journal-title":"Sci. Rob."},{"key":"861_CR4","doi-asserted-by":"publisher","first-page":"eabc5986","DOI":"10.1126\/scirobotics.abc5986","volume":"5","author":"J Lee","year":"2020","unstructured":"Lee, J., Hwangbo, J., Wellhausen, L., Koltun, V. & Hutter, M. Learning quadrupedal locomotion over challenging terrain. Sci. Rob. 5, eabc5986 (2020).","journal-title":"Sci. Rob."},{"key":"861_CR5","doi-asserted-by":"publisher","first-page":"eabk2822","DOI":"10.1126\/scirobotics.abk2822","volume":"7","author":"T Miki","year":"2022","unstructured":"Miki, T. et al. Learning robust perceptive locomotion for quadrupedal robots in the wild. Sci. Rob. 7, eabk2822 (2022).","journal-title":"Sci. Rob."},{"key":"861_CR6","doi-asserted-by":"crossref","unstructured":"Kumar, A., Fu, Z., Pathak, D. & Malik, J. RMA: rapid motor adaptation for legged robots. In Proc. Robotics: Science and Systems Vol. XVII (2021).","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"861_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, X., Shi, K., Agarwal, A. & Pathak, D. Extreme parkour with legged robots. In Conference on Robot Learning (2023).","DOI":"10.1109\/ICRA57147.2024.10610200"},{"key":"861_CR8","unstructured":"Zhuang, Z. et al. Robot parkour learning. In Conference on Robot Learning (2023)."},{"key":"861_CR9","doi-asserted-by":"publisher","first-page":"eadi7566","DOI":"10.1126\/scirobotics.adi7566","volume":"9","author":"D Hoeller","year":"2024","unstructured":"Hoeller, D., Rudin, N., Sako, D. & Hutter, M. ANYmal parkour: learning agile navigation for quadrupedal robots. Sci. Rob. 9, eadi7566 (2024).","journal-title":"Sci. Rob."},{"key":"861_CR10","unstructured":"Yang, Y. et al. CAJun: continuous adaptive jumping using a learned centroidal controller. In Proc. 7th Conference on Robot Learning Vol. 229, 2791\u20132806 (PMLR, 2023)."},{"key":"861_CR11","doi-asserted-by":"publisher","unstructured":"Caluwaerts, K. et al. Barkour: benchmarking animal-level agility with quadruped robots. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2305.14654 (2023).","DOI":"10.48550\/arXiv.2305.14654"},{"key":"861_CR12","doi-asserted-by":"publisher","first-page":"eade2256","DOI":"10.1126\/scirobotics.ade2256","volume":"8","author":"S Choi","year":"2023","unstructured":"Choi, S. et al. Learning quadrupedal locomotion on deformable terrain. Sci. Rob. 8, eade2256 (2023).","journal-title":"Sci. Rob."},{"key":"861_CR13","doi-asserted-by":"publisher","first-page":"eabb2174","DOI":"10.1126\/scirobotics.abb2174","volume":"5","author":"C Yang","year":"2020","unstructured":"Yang, C., Yuan, K., Zhu, Q., Yu, W. & Li, Z. Multi-expert learning of adaptive legged locomotion. Sci. Rob. 5, eabb2174 (2020).","journal-title":"Sci. Rob."},{"key":"861_CR14","unstructured":"Peng, X. B. et al. Learning agile robotic locomotion skills by imitating animals. In Proc. Robotics: Science and Systems (2020)."},{"key":"861_CR15","doi-asserted-by":"publisher","unstructured":"Bohez, S. et al. Imitate and repurpose: learning reusable robot movement skills from human and animal behaviors. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2203.17138 (2022).","DOI":"10.48550\/arXiv.2203.17138"},{"key":"861_CR16","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1145\/2185520.2185524","volume":"31","author":"S Levine","year":"2012","unstructured":"Levine, S., Wang, J. M., Haraux, A., Popovi\u0107, Z. & Koltun, V. Continuous character control with low-dimensional embeddings. ACM Trans. Graphics 31, 28 (2012).","journal-title":"ACM Trans. Graphics"},{"key":"861_CR17","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1145\/3386569.3392422","volume":"39","author":"HY Ling","year":"2020","unstructured":"Ling, H. Y., Zinno, F., Cheng, G. & Van De Panne, M. Character controllers using motion VAEs. ACM Trans. Graphics 39, 40 (2020).","journal-title":"ACM Trans. Graphics"},{"key":"861_CR18","first-page":"9989","volume":"23","author":"D Tirumala","year":"2022","unstructured":"Tirumala, D. et al. Behavior priors for efficient reinforcement learning. J. Mach. Learn. Res. 23, 9989\u201310056 (2022).","journal-title":"J. Mach. Learn. Res."},{"key":"861_CR19","doi-asserted-by":"publisher","unstructured":"Heess, N. et al. Learning and transfer of modulated locomotor controllers. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1610.05182 (2016).","DOI":"10.48550\/arXiv.1610.05182"},{"key":"861_CR20","unstructured":"Merel, J. et al. Neural probabilistic motor primitives for humanoid control. In International Conference on Learning Representations 4647\u20134660 (Curran Assoc., 2019)."},{"key":"861_CR21","unstructured":"Hasenclever, L., Pardo, F., Hadsell, R., Heess, N. & Merel, J. CoMic: complementary task learning & mimicry for reusable skills. In Proc. 37th International Conference on Machine Learning Vol. 119, 4105\u20134115 (PMLR, 2020)."},{"key":"861_CR22","doi-asserted-by":"publisher","first-page":"eabo0235","DOI":"10.1126\/scirobotics.abo0235","volume":"7","author":"S Liu","year":"2022","unstructured":"Liu, S. et al. From motor control to team play in simulated humanoid football. Sci. Rob. 7, eabo0235 (2022).","journal-title":"Sci. Rob."},{"key":"861_CR23","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1145\/3618397","volume":"42","author":"Q Zhu","year":"2023","unstructured":"Zhu, Q., Zhang, H., Lan, M. & Han, L. Neural categorical priors for physics-based character control. ACM Trans. Graphics 42, 178 (2023).","journal-title":"ACM Trans. Graphics"},{"key":"861_CR24","doi-asserted-by":"crossref","unstructured":"Ji, Y. et al. Hierarchical reinforcement learning for precise soccer shooting skills using a quadrupedal robot. In 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems 1479\u20131486 (IEEE, 2022).","DOI":"10.1109\/IROS47612.2022.9981984"},{"key":"861_CR25","unstructured":"van den Oord, A., Vinyals, O. & Kavukcuoglu, K. Neural discrete representation learning. In Advances in Neural Information Processing Systems (2017)."},{"key":"861_CR26","unstructured":"Ramesh, A. et al. Zero-shot text-to-image generation. In Proc. 38th International Conference on Machine Learning Vol. 139, 8821\u20138831 (PMLR, 2021)."},{"key":"861_CR27","doi-asserted-by":"publisher","unstructured":"Roy, A., Vaswani, A., Neelakantan, A. & Parmar, N. Theory and experiments on vector quantized autoencoders. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1805.11063 (2018).","DOI":"10.48550\/arXiv.1805.11063"},{"key":"861_CR28","unstructured":"Bishop, C. M. & Nasrabadi, N. M. Pattern Recognition and Machine Learning Vol. 4 (Springer, 2006)."},{"key":"861_CR29","doi-asserted-by":"crossref","unstructured":"Chi, W., Jiang, X. & Zheng, Y. A linearization of centroidal dynamics for the model-predictive control of quadruped robots. In 2022 International Conference on Robotics and Automation 4656\u20134663 (IEEE, 2022).","DOI":"10.1109\/ICRA46639.2022.9812433"},{"key":"861_CR30","doi-asserted-by":"crossref","unstructured":"Zhou, Q. et al. Max: A wheeled-legged quadruped robot for multimodal agile locomotion. IEEE Transactions on Automation Science and Engineering 1\u201321 (2024).","DOI":"10.1109\/TASE.2023.3345876"},{"key":"861_CR31","doi-asserted-by":"publisher","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A. & Klimov, O. Proximal policy optimization algorithms. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1707.06347 (2017).","DOI":"10.48550\/arXiv.1707.06347"},{"key":"861_CR32","doi-asserted-by":"publisher","unstructured":"Sun, P. et al. TLeague: a framework for competitive self-play based distributed multi-agent reinforcement learning. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2011.12895 (2020).","DOI":"10.48550\/arXiv.2011.12895"},{"key":"861_CR33","unstructured":"Higgins, I. et al. beta-VAE: learning basic visual concepts with a constrained variational framework. In International Conference on Learning Representations (2017)."},{"key":"861_CR34","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten, L. & Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008).","journal-title":"J. Mach. Learn. Res."},{"key":"861_CR35","first-page":"707","volume":"689","author":"A Gouelle","year":"2018","unstructured":"Gouelle, A., M\u00e9grot, F. & M\u00fcller, B. Interpreting spatiotemporal parameters, symmetry, and variability in clinical gait analysis. Handb. Hum. Motion 689, 707 (2018).","journal-title":"Handb. Hum. Motion"},{"key":"861_CR36","doi-asserted-by":"publisher","first-page":"1155","DOI":"10.2460\/ajvr.74.9.1155","volume":"74","author":"SL Jarvis","year":"2013","unstructured":"Jarvis, S. L. et al. Kinematic and kinetic analysis of dogs during trotting after amputation of a thoracic limb. Am. J. Vet. Res. 74, 1155\u20131163 (2013).","journal-title":"Am. J. Vet. Res."},{"key":"861_CR37","doi-asserted-by":"crossref","unstructured":"P\u00e1lya, Z., R\u00e1cz, K., Nagym\u00e1t\u00e9, G. & Kiss, R. M. Development of a detailed canine gait analysis method for evaluating harnesses: a pilot study. PLoS ONE 17, e0264299 (2022).","DOI":"10.1371\/journal.pone.0264299"},{"key":"861_CR38","unstructured":"World chase tag. Wikipedia https:\/\/en.wikipedia.org\/wiki\/World_Chase_Tag (accessed 23 March 2023)."},{"key":"861_CR39","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O. et al. Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575, 350\u2013354 (2019).","journal-title":"Nature"},{"key":"861_CR40","doi-asserted-by":"publisher","unstructured":"Han, L. et al. TStarBot-X: an open-sourced and comprehensive study for efficient league training in starcraft ii full game. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2011.13729 (2020).","DOI":"10.48550\/arXiv.2011.13729"},{"key":"861_CR41","unstructured":"Coulom, R. Bayesian Elo rating (2005)."},{"key":"861_CR42","unstructured":"Xie, Z. et al. Learning locomotion skills for cassie: Iterative design and sim-to-real. In Proc. Conference on Robot Learning, volume 100 of Proceedings of Machine Learning Research 317\u2013329 (PMLR, 2020)."},{"key":"861_CR43","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1145\/3272127.3275014","volume":"37","author":"XB Peng","year":"2018","unstructured":"Peng, X. B., Kanazawa, A., Malik, J., Abbeel, P. & Levine, S. SFV: reinforcement learning of physical skills from videos. ACM Trans. Graph. 37, 178 (2018).","journal-title":"ACM Trans. Graph."},{"key":"861_CR44","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1145\/3592408","volume":"42","author":"H Zhang","year":"2023","unstructured":"Zhang, H. et al. Learning physically simulated tennis skills from broadcast videos. ACM Trans. Graph. 42, 95 (2023).","journal-title":"ACM Trans. Graph."},{"key":"861_CR45","doi-asserted-by":"crossref","unstructured":"Gleicher, M. Retargetting motion to new characters. In Proc. 25th Annual Conference on Computer Graphics and Interactive Techniques 33\u201342 (Association for Computing Machinery, 1998).","DOI":"10.1145\/280814.280820"},{"key":"861_CR46","doi-asserted-by":"crossref","unstructured":"Peng, X. B. and Van De Panne, M. Learning locomotion skills using DeepRL: does the choice of action space matter? In Proc. ACM SIGGRAPH\/Eurographics Symposium on Computer Animation 12:1\u201312:13 (Association for Computing Machinery, 2017).","DOI":"10.1145\/3099564.3099567"},{"key":"861_CR47","unstructured":"Ho, J. and Ermon, S. Generative adversarial imitation learning. In Advances in Neural Information Processing Systems Vol. 29 (2016)."},{"key":"861_CR48","unstructured":"Agarwal, A., Kumar, A., Malik, J. & Pathak, D. Legged locomotion in challenging terrains using egocentric vision. In Proc. 6th Conference on Robot Learning (eds Liu, K. et al.) 403\u2013415 (PMLR, 2023)."},{"key":"861_CR49","doi-asserted-by":"crossref","unstructured":"Li, T. et al. Learning terrain-adaptive locomotion with agile behaviors by imitating animals. In 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems 339\u2013345, (2023).","DOI":"10.1109\/IROS55552.2023.10342271"},{"key":"861_CR50","doi-asserted-by":"publisher","unstructured":"Rusu, A. A. et al. Policy distillation. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1511.06295 (2015).","DOI":"10.48550\/arXiv.1511.06295"},{"key":"861_CR51","doi-asserted-by":"publisher","unstructured":"Han, L. et al. Lifelike agility and play in quadrupedal robots using reinforcement learning and generative pre-trained models. Code Ocean https:\/\/doi.org\/10.24433\/CO.8441152.v3 (2024).","DOI":"10.24433\/CO.8441152.v3"}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00861-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00861-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00861-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T09:06:21Z","timestamp":1732352781000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00861-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,5]]},"references-count":51,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2024,7]]}},"alternative-id":["861"],"URL":"https:\/\/doi.org\/10.1038\/s42256-024-00861-3","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-3309878\/v1","asserted-by":"object"}]},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,5]]},"assertion":[{"value":"30 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 May 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}