{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T11:03:12Z","timestamp":1772276592621,"version":"3.50.1"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T00:00:00Z","timestamp":1768089600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T00:00:00Z","timestamp":1768089600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,11]]},"DOI":"10.1109\/sii64115.2026.11404486","type":"proceedings-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:47:13Z","timestamp":1772225233000},"page":"325-332","source":"Crossref","is-referenced-by-count":0,"title":["Learning Humanoid Loco-manipulation with Constraints as Terminations"],"prefix":"10.1109","author":[{"given":"Pierre-Alexandre","family":"Leziart","sequence":"first","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST),CNRS-AIST JRL (Joint Robotics Laboratory),Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mitsuharu","family":"Morisawa","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST),CNRS-AIST JRL (Joint Robotics Laboratory),Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fumio","family":"Kanehiro","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST),CNRS-AIST JRL (Joint Robotics Laboratory),Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Robot parkour learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Zhuang"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610200"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abp9742"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3084374"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241312698"},{"key":"ref6","article-title":"Humanoid parkour learning","author":"Zhuang","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-025-11451-z"},{"key":"ref8","volume-title":"Quadruped products","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1487\/1\/012048"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802334"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981539"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3192581"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3400935"},{"key":"ref14","article-title":"Evaluation of constrained reinforcement learning algorithms for legged locomotion","author":"Lee","year":"2023"},{"key":"ref15","article-title":"The 37 implementation details of proximal policy optimization","volume-title":"ICLR Blog Track","author":"Huang","year":"2022"},{"key":"ref16","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref17","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"Makoviychuk","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3093551"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3320827"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3396025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610069"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09997-9"},{"issue":"268","key":"ref23","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume-title":"Journal of Machine Learning Research","volume":"22","author":"Raffin","year":"2021"},{"issue":"274","key":"ref24","first-page":"1","article-title":"Cleanrl: High-quality single-file implementations of deep reinforcement learning algorithms","volume-title":"Journal of Machine Learning Research","volume":"23","author":"Huang","year":"2022"},{"key":"ref25","article-title":"Implementation matters in deep policy gradients: A case study on ppo and trpo","volume-title":"International Conference on Learning Representations","author":"Engstrom"},{"key":"ref26","article-title":"What matters in on-policy reinforcement learning? a large-scale empirical study","volume-title":"ICLR 2021-Ninth International Conference on Learning Representations","author":"Andrychowicz"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids57100.2023.10375148"},{"key":"ref29","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Conference on Robot Learning","author":"Rudin"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-38259-7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s43154-022-00082-9"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610449"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801451"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids57100.2023.10375203"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383296"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3606931"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610977"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561559"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560837"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201397"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3359566.3360070"},{"key":"ref45","article-title":"rl-games: A high-performance framework for reinforcement learning","author":"Makoviichuk","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981198"}],"event":{"name":"2026 IEEE\/SICE International Symposium on System Integration (SII)","location":"Cancun, Mexico","start":{"date-parts":[[2026,1,11]]},"end":{"date-parts":[[2026,1,14]]}},"container-title":["2026 IEEE\/SICE International Symposium on System Integration (SII)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11404435\/11404394\/11404486.pdf?arnumber=11404486","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T06:38:45Z","timestamp":1772260725000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11404486\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,11]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/sii64115.2026.11404486","relation":{},"subject":[],"published":{"date-parts":[[2026,1,11]]}}}