{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T04:51:17Z","timestamp":1761367877004,"version":"build-2065373602"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"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":[[2025,9,30]]},"DOI":"10.1109\/humanoids65713.2025.11203130","type":"proceedings-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T17:15:50Z","timestamp":1761326150000},"page":"882-889","source":"Crossref","is-referenced-by-count":0,"title":["Mechanical Intelligence-Aware Curriculum Reinforcement Learning for Humanoids with Parallel Actuation"],"prefix":"10.1109","author":[{"given":"Yusuke","family":"Tanaka","sequence":"first","affiliation":[{"name":"UCLA,Department of Mechanical and Aerospace Engineering,Los Angeles,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alvin","family":"Zhu","sequence":"additional","affiliation":[{"name":"UCLA,Department of Mechanical and Aerospace Engineering,Los Angeles,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quanyou","family":"Wang","sequence":"additional","affiliation":[{"name":"UCLA,Department of Mechanical and Aerospace Engineering,Los Angeles,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dennis","family":"Hong","sequence":"additional","affiliation":[{"name":"UCLA,Department of Mechanical and Aerospace Engineering,Los Angeles,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS47582.2021.9555782"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811790"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi9579"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi8022"},{"key":"ref5","article-title":"Optimal control of walkers with parallel actuation","author":"De Matteis","year":"2025","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2528294"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids43949.2019.9035071"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids58906.2024.10769903"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981555"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1117\/12.2231105"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354188"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594355"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916648388"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594182"},{"article-title":"On the hardware design and control architecture of the humanoid robot kangaroo","volume-title":"6th workshop on legged robots during the international conference on robotics and automation","author":"Roig","key":"ref15"},{"article-title":"Scaler-b: A multimodal versatile robot for simultaneous locomotion and grasping","volume-title":"IEEE International Conference on Robotics and Automation 40","author":"Tanaka","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3342667"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610947"},{"key":"ref19","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref20","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning","author":"Schulman"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CAIBDA53561.2021.00025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids58906.2024.10769793"},{"journal-title":"Reinforcement learning in robotics: Challenges and opportunities","year":"2023","author":"Kaleem","key":"ref24"},{"journal-title":"Scaling data-driven robotics with reward sketching and batch reinforcement learning","year":"2020","author":"Cabi","key":"ref25"},{"key":"ref26","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","author":"Rudin","year":"2022","journal-title":"arXiv"},{"journal-title":"Transic: Sim-to-real policy transfer by learning from online correction","year":"2024","author":"Jiang","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"journal-title":"Continual domain randomization","year":"2024","author":"Josifovski","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802145"},{"journal-title":"Learning humanoid locomotion with transformers","year":"2023","author":"Radosavovic","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341617"},{"journal-title":"Curriculum learning for reinforcement learning domains: A framework and survey","year":"2020","author":"Narvekar","key":"ref33"},{"journal-title":"Reverse curriculum generation for reinforcement learning","year":"2018","author":"Florensa","key":"ref34"},{"key":"ref35","article-title":"Aura: Agentic upskilling via reinforced abstractions","author":"Zhu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref37","first-page":"9797","article-title":"Safe reinforcement learning in constrained markov decision processes","volume-title":"International Conference on Machine Learning","author":"Wachi"},{"journal-title":"An efficient orientation filter for inertial and inertial\/magnetic sensor arrays","year":"2010","author":"Madgwick","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids53995.2022.10000075"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2025.3588446"}],"event":{"name":"2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids)","start":{"date-parts":[[2025,9,30]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2025,10,2]]}},"container-title":["2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11202977\/11203009\/11203130.pdf?arnumber=11203130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T04:46:46Z","timestamp":1761367606000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11203130\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,30]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/humanoids65713.2025.11203130","relation":{},"subject":[],"published":{"date-parts":[[2025,9,30]]}}}