{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T18:46:30Z","timestamp":1784054790888,"version":"3.55.0"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610086","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"11459-11466","source":"Crossref","is-referenced-by-count":9,"title":["Robust Quadrupedal Locomotion via Risk-Averse Policy Learning"],"prefix":"10.1109","author":[{"given":"Jiyuan","family":"Shi","sequence":"first","affiliation":[{"name":"Tsinghua University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenjia","family":"Bai","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Han","sequence":"additional","affiliation":[{"name":"Tencent Robotics X,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingguo","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiu","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2798285"},{"key":"ref2","article-title":"Highly dynamic quadruped locomotion via whole-body impulse control and model predictive control","author":"Kim","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref4","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Makoviychuk"},{"key":"ref5","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Rudin"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161144"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00144"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982190"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref13","article-title":"Legged locomotion in challenging terrains using egocentric vision","volume-title":"6th Annual Conference on Robot Learning (CoRL)","author":"Agarwal"},{"key":"ref14","article-title":"Learning to walk via deep reinforcement learning","author":"Haarnoja","year":"2019","journal-title":"Robotics: Science and Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981072"},{"key":"ref16","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Rudin"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00600"},{"key":"ref18","first-page":"1184","article-title":"Decomposition of uncertainty in bayesian deep learning for efficient and risk-sensitive learning","volume-title":"International Conference on Machine Learning","author":"Depeweg"},{"key":"ref19","article-title":"Aliengo - Multifunctional, Industrial Level Application - Unitree"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.ade2256"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.55417\/fr.2023013"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3151396"},{"key":"ref23","article-title":"Privileged knowledge distillation for sim-to-real policy generalization","author":"He","year":"2023"},{"key":"ref24","article-title":"Learning vision-guided quadrupedal locomotion end-to-end with cross-modal transformers","volume-title":"International Conference on Learning Representations (ICLR)","author":"Yang"},{"key":"ref25","article-title":"Robust recovery controller for a quadrupedal robot using deep reinforcement learning","author":"Lee","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160582"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.2307\/3213832"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176342415"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/BF00938524"},{"key":"ref30","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"International conference on Machine Learning","author":"Bellemare"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref32","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"International conference on Machine Learning","author":"Dabney"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2143\/AST.26.1.563234"},{"key":"ref34","first-page":"1406","article-title":"Cumulative prospect theory meets reinforcement learning: Prediction and control","volume-title":"International Conference on Machine Learning","author":"Prashanth"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21314\/JOR.2000.038"},{"key":"ref36","article-title":"Algorithms for cvar optimization in mdps","volume":"27","author":"Chow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref37","article-title":"Risk-averse offline reinforcement learning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Urp\u00ed"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29188"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3217189"},{"key":"ref40","article-title":"Conservative safety critics for exploration","author":"Bharadhwaj","year":"2020"},{"key":"ref41","first-page":"4424","article-title":"Distributional reinforcement learning for efficient exploration","volume-title":"International conference on Machine Learning","author":"Mavrin"},{"key":"ref42","first-page":"15 220","article-title":"How to stay curious while avoiding noisy tvs using aleatoric uncertainty estimation","volume-title":"International Conference on Machine Learning","author":"Mavor-Parker"},{"key":"ref43","article-title":"Worst cases policy gradients","author":"Tang","year":"2019"},{"key":"ref44","article-title":"Risk-averse offline reinforcement learning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Urp\u00ed"},{"key":"ref45","first-page":"19 235","article-title":"Conservative offline distributional reinforcement learning","volume":"34","author":"Ma","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi8022"},{"key":"ref47","article-title":"Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning","author":"Schneider","year":"2023"},{"key":"ref48","first-page":"7927","article-title":"Gmac: A distributional perspective on actor-critic framework","volume-title":"International Conference on Machine Learning","author":"Nam"},{"key":"ref49","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"4th International Conference on Learning Representations (ICLR)","author":"Schulman"},{"key":"ref50","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982132"},{"key":"ref52","article-title":"Z1 - Dexterous Robotic Arm, Perfect Coordination - Unitree"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610086.pdf?arnumber=10610086","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:43:59Z","timestamp":1723268639000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610086\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610086","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}