{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T22:03:38Z","timestamp":1772057018516,"version":"3.50.1"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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","award":["62403064"],"award-info":[{"award-number":["62403064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62403063"],"award-info":[{"award-number":["62403063"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["ZDCY20250901094531003"],"award-info":[{"award-number":["ZDCY20250901094531003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2026.3662755","type":"journal-article","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T20:52:49Z","timestamp":1771015969000},"page":"4861-4876","source":"Crossref","is-referenced-by-count":0,"title":["ECO: Energy-Constrained Optimization With Reinforcement Learning for Humanoid Walking"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9286-6492","authenticated-orcid":false,"given":"Weidong","family":"Huang","sequence":"first","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1508-1358","authenticated-orcid":false,"given":"Jingwen","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI), Beijing, China"}]},{"given":"Jiongye","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2934-4589","authenticated-orcid":false,"given":"Shibowen","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI), Beijing, China"}]},{"given":"Jiayang","family":"Wu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1313-138X","authenticated-orcid":false,"given":"Jiayi","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3003-8611","authenticated-orcid":false,"given":"Hangxin","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8132-5613","authenticated-orcid":false,"given":"Yaodong","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence and the School of Artificial Intelligence, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8375-5692","authenticated-orcid":false,"given":"Yao","family":"Su","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI), Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802062"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3408487"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342265"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/rob.22588"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-32552-1_48"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3443589"},{"key":"ref7","article-title":"Minimizing energy consumption leads to the emergence of gaits in legged robots","author":"Fu","year":"2021","journal-title":"arXiv:2111.01674"},{"key":"ref8","article-title":"HumanPlus: Humanoid shadowing and imitation from humans","author":"Fu","year":"2024","journal-title":"arXiv:2406.10454"},{"key":"ref9","article-title":"Humanoid-gym: Reinforcement learning for humanoid robot with zero-shot Sim2Real transfer","author":"Gu","year":"2024","journal-title":"arXiv:2404.05695"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160885"},{"issue":"167","key":"ref11","first-page":"1","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26734"},{"key":"ref13","article-title":"SafeDreamer: Safe reinforcement learning with world models","author":"Huang","year":"2023","journal-title":"arXiv:2307.07176"},{"key":"ref14","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3400935"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1126\/science.1107799"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1302452"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9479-3"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids53995.2022.10000075"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915612572"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.3048125"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3392154"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611056"},{"key":"ref24","first-page":"3439","article-title":"Adapting humanoid locomotion over challenging terrain via two-phase training","volume-title":"Proc. 8th Annu. Conf. Robot Learn.","author":"Cui"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2023.3234269"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2518"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561814"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981091"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801468"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids58906.2024.10769914"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201397"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802439"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530110"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s12293-022-00357-w"},{"key":"ref36","article-title":"Human-in-the-loop policy optimization for preference-based multi-objective reinforcement learning","author":"Li","year":"2024","journal-title":"arXiv:2401.02160"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2024.3425629"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29488"},{"key":"ref40","article-title":"Constrained reinforcement learning has zero duality gap","author":"Paternain","year":"2019","journal-title":"arXiv:1910.13393"},{"key":"ref41","article-title":"Benchmarking batch deep reinforcement learning algorithms","author":"Ray","year":"2019","journal-title":"arXiv:1910.01708"},{"key":"ref42","first-page":"1357","article-title":"Robot reinforcement learning on the constraint manifold","volume-title":"Proc. Conf. Robot Learn.","author":"Liu"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3326922"},{"key":"ref44","first-page":"11480","article-title":"CRPO: A new approach for safe reinforcement learning with convergence guarantee","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Xu"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5932"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/520"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801341"},{"key":"ref48","first-page":"18964","article-title":"Safety gymnasium: A unified safe reinforcement learning benchmark","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Ji"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.058"},{"key":"ref50","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref51","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref52","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"},{"key":"ref53","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Rudin"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811790"},{"key":"ref56","volume-title":"BRUCE, A Kid-Size Humanoid Robot Open-Platform for Research and Education","year":"2024"},{"key":"ref57","first-page":"270","article-title":"Gpu-accelerated robotic simulation for distributed reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Liang"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.008"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3301175"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389727"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1242\/jeb.02455"},{"key":"ref63","article-title":"Mastering diverse domains through world models","author":"Hafner","year":"2023","journal-title":"arXiv:2301.04104"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914566516"},{"key":"ref65","article-title":"Learning to walk from three minutes of real-world data with semi-structured dynamics models","author":"Levy","year":"2024","journal-title":"arXiv:2410.09163"},{"key":"ref66","article-title":"Constrained policy optimization via Bayesian world models","author":"As","year":"2022","journal-title":"arXiv:2201.09802"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adg5014"},{"key":"ref68","article-title":"Learning to open and traverse doors with a legged manipulator","author":"Zhang","year":"2024","journal-title":"arXiv:2409.04882"},{"key":"ref69","first-page":"403","article-title":"Legged locomotion in challenging terrains using egocentric vision","volume-title":"Proc. Conf. Robot Learn.","author":"Agarwal"},{"key":"ref70","article-title":"SoloParkour: Constrained reinforcement learning for visual locomotion from privileged experience","author":"Chane-Sane","year":"2024","journal-title":"arXiv:2409.13678"},{"key":"ref71","first-page":"1291","article-title":"Visual-locomotion: Learning to walk on complex terrains with vision","volume-title":"Proc. 5th Annu. Conf. Robot Learn.","author":"Yu"},{"key":"ref72","article-title":"Hierarchical world models as visual whole-body humanoid controllers","author":"Hansen","year":"2024","journal-title":"arXiv:2405.18418"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3143567"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11396018.pdf?arnumber=11396018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T20:59:43Z","timestamp":1772053183000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11396018\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/tase.2026.3662755","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}