{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T12:09:41Z","timestamp":1761480581816,"version":"build-2065373602"},"publisher-location":"Singapore","reference-count":18,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819520978"},{"type":"electronic","value":"9789819520985"}],"license":[{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-2098-5_33","type":"book-chapter","created":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T12:01:08Z","timestamp":1761480068000},"page":"385-396","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Agile and\u00a0Versatile Bipedal Robot Tracking Control Through Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Han","family":"Zheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linqi","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Houde","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"33_CR1","doi-asserted-by":"crossref","unstructured":"Arm, P., et\u00a0al.: Scientific exploration of challenging planetary analog environments with a team of legged robots. Sci. Robot. 8(80), eade9548 (2023)","DOI":"10.1126\/scirobotics.ade9548"},{"key":"33_CR2","unstructured":"Brohan, A., et\u00a0al.: Rt-1: Robotics transformer for real-world control at scale. arXiv preprint arXiv:2212.06817 (2022)"},{"key":"33_CR3","unstructured":"Chen, D., Zhou, B., Koltun, V., Kr\u00e4henb\u00fchl, P.: Learning by cheating. In: Conference on robot learning, pp. 66\u201375. PMLR (2020)"},{"key":"33_CR4","unstructured":"Cornell: 12-joint ranger max robot model. http:\/\/ruina.tam.cornell.edu\/research\/topics\/locomotion_and_robotics\/Tik-Tok"},{"issue":"5","key":"33_CR5","doi-asserted-by":"publisher","first-page":"2908","DOI":"10.1109\/TRO.2022.3172469","volume":"38","author":"S Gangapurwala","year":"2022","unstructured":"Gangapurwala, S., Geisert, M., Orsolino, R., Fallon, M., Havoutis, I.: RLOC: terrain-aware legged locomotion using reinforcement learning and optimal control. IEEE Trans. Rob. 38(5), 2908\u20132927 (2022)","journal-title":"IEEE Trans. Rob."},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Hwangbo, J., et al.: Learning agile and dynamic motor skills for legged robots. Sci. Robot. 4(26), eaau5872 (2019)","DOI":"10.1126\/scirobotics.aau5872"},{"key":"33_CR7","doi-asserted-by":"crossref","unstructured":"Jenelten, F., He, J., Farshidian, F., Hutter, M.: DTC: deep tracking control. Sci. Robot. 9(86), eadh5401 (2024)","DOI":"10.1126\/scirobotics.adh5401"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Kumar, A., Fu, Z., Pathak, D., Malik, J.: RMA: rapid motor adaptation for legged robots. arXiv preprint arXiv:2107.04034 (2021)","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Melon, O., Geisert, M., Surovik, D., Havoutis, I., Fallon, M.: Reliable trajectories for dynamic quadrupeds using analytical costs and learned initializations. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 1410\u20131416. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9196562"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Melon, O., et al.: Receding-horizon perceptive trajectory optimization for dynamic legged locomotion with learned initialization. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 9805\u20139811. IEEE (2021)","DOI":"10.1109\/ICRA48506.2021.9560794"},{"issue":"4","key":"33_CR11","first-page":"1","volume":"37","author":"XB Peng","year":"2018","unstructured":"Peng, X.B., Abbeel, P., Levine, S., Panne, M.: Deepmimic: example-guided deep reinforcement learning of physics-based character skills. ACM Trans. Graph. (TOG) 37(4), 1\u201314 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"Peng, X.B., Andrychowicz, M., Zaremba, W., Abbeel, P.: Sim-to-real transfer of robotic control with dynamics randomization. In: 2018 IEEE international conference on robotics and automation (ICRA), pp. 3803\u20133810. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460528"},{"issue":"4","key":"33_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530110","volume":"41","author":"XB Peng","year":"2022","unstructured":"Peng, X.B., Guo, Y., Halper, L., Levine, S., Fidler, S.: ASE: Large-scale reusable adversarial skill embeddings for physically simulated characters. ACM Trans. Graph. (TOG) 41(4), 1\u201317 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"33_CR14","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"33_CR15","unstructured":"Vezhnevets, A.S., et al.: Feudal networks for hierarchical reinforcement learning. In: International conference on machine learning, pp. 3540\u20133549. PMLR (2017)"},{"issue":"9","key":"33_CR16","first-page":"4555","volume":"44","author":"X Wang","year":"2021","unstructured":"Wang, X., Chen, Y., Zhu, W.: A survey on curriculum learning. IEEE Trans. Pattern Anal. Mach. Intell. 44(9), 4555\u20134576 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"33_CR17","unstructured":"Yang, Y., Zhang, T., Coumans, E., Tan, J., Boots, B.: Fast and efficient locomotion via learned gait transitions. In: Conference on Robot Learning, pp. 773\u2013783. PMLR (2022)"},{"key":"33_CR18","unstructured":"Ye, L., Li, J., Cheng, Y., Wang, X., Liang, B., Peng, Y.: From knowing to doing: learning diverse motor skills through instruction learning. arXiv preprint arXiv:2309.09167 (2023)"}],"container-title":["Lecture Notes in Computer Science","Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-2098-5_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T12:01:16Z","timestamp":1761480076000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-2098-5_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"ISBN":["9789819520978","9789819520985"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-2098-5_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"27 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIRA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Robotics and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okayama","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icira2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.icira2025.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}