{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:40:48Z","timestamp":1766061648722,"version":"3.48.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246723","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"10656-10663","source":"Crossref","is-referenced-by-count":0,"title":["ARC: Robots Adaptive Risk-aware Robust Control via Distributional Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Junlong","family":"Wu","sequence":"first","affiliation":[{"name":"Tsinghua University,Beijing,China,100084"}]},{"given":"Yi","family":"Cheng","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China,100084"}]},{"given":"Hang","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Michigan,Ann Arbor,MI,USA,48109"}]},{"given":"Houde","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China,100084"}]}],"member":"263","reference":[{"article-title":"Robot parkour learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Zhuang","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610200"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610086"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610137"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801507"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460731"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161144"},{"article-title":"Mbc: Multi-brain collaborative control for quadruped robots","year":"2024","author":"Liu","key":"ref10"},{"key":"ref11","article-title":"Legged locomotion in challenging terrains using egocentric vision","author":"Agarwal","year":"2022","journal-title":"CoRL"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi7566"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2024.XX.059","article-title":"Agile but safe: Learning collision-free high-speed legged locomotion","author":"He","year":"2024"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2021.XVII.061","article-title":"Blind bipedal stair traversal via sim-to-real reinforcement learning","author":"Siekmann","year":"2021"},{"article-title":"Humanoid parkour learning","year":"2024","author":"Zhuang","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241285161"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi9579"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2024.XX.058","article-title":"Advancing humanoid locomotion: Mastering challenging terrains with denoising world model learning","author":"Gu","year":"2024"},{"article-title":"Berkeley humanoid: A research platform for learning-based control","year":"2024","author":"Liao","key":"ref19"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2024.XX.107","article-title":"Expressive whole-body control for humanoid robots","author":"Cheng","year":"2024"},{"article-title":"Wococo: Learning whole-body humanoid control with sequential contacts","year":"2024","author":"Zhang","key":"ref21"},{"key":"ref22","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"International conference on machine learning","author":"Bellemare"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref24","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Dabney"},{"key":"ref25","article-title":"Fully parameterized quantile function for distributional reinforcement learning","volume":"32","author":"Yang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref26","first-page":"7927","article-title":"Gmac: A distributional perspective on actor-critic framework","volume-title":"International Conference on Machine Learning","author":"Nam"},{"article-title":"Distributed distributional deterministic policy gradients","year":"2018","author":"Barth-Maron","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"article-title":"Worst cases policy gradients","year":"2019","author":"Tang","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5220\/0008175604120423"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00600"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/a16070325"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2939-8"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi8022"},{"article-title":"Learning h-infinity locomotion control","year":"2024","author":"Long","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-012-9200-2"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307420"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.2307\/253675"},{"article-title":"Automatic risk adaptation in distributional reinforcement learning","year":"2021","author":"Schubert","key":"ref39"},{"article-title":"Exploration by random network distillation","year":"2018","author":"Burda","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246723.pdf?arnumber=11246723","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:37:01Z","timestamp":1766061421000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246723\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246723","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}