{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T10:49:57Z","timestamp":1779101397568,"version":"3.51.4"},"reference-count":43,"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\/icra57147.2024.10610856","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"2838-2844","source":"Crossref","is-referenced-by-count":1,"title":["Offline Goal-Conditioned Reinforcement Learning for Safety-Critical Tasks with Recovery Policy"],"prefix":"10.1109","author":[{"given":"Chenyang","family":"Cao","sequence":"first","affiliation":[{"name":"Center for Intelligent Control and Telescience, Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zichen","family":"Yan","sequence":"additional","affiliation":[{"name":"Center for Intelligent Control and Telescience, Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renhao","family":"Lu","sequence":"additional","affiliation":[{"name":"Center for Intelligent Control and Telescience, Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junbo","family":"Tan","sequence":"additional","affiliation":[{"name":"Center for Intelligent Control and Telescience, Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueqian","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Intelligent Control and Telescience, Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812166"},{"key":"ref2","first-page":"490","article-title":"Learning to manipulate object collections using grounded state representations","volume-title":"Conference on Robot Learning","author":"Wilson"},{"key":"ref3","first-page":"138","article-title":"Deep whole-body control: learning a unified policy for manipulation and locomotion","volume-title":"Conference on Robot Learning","author":"Fu"},{"key":"ref4","first-page":"212","article-title":"i-sim2real: Reinforcement learning of robotic policies in tight humanrobot interaction loops","volume-title":"Conference on Robot Learning","author":"Abeyruwan"},{"key":"ref5","first-page":"55","article-title":"Graph inverse reinforcement learning from diverse videos","volume-title":"Conference on Robot Learning","author":"Kumar"},{"key":"ref6","article-title":"Hindsight policy gradients","volume-title":"International Conference on Learning Representations","author":"Rauber"},{"key":"ref7","article-title":"Hind-sight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Learning to reach goals via iterated supervised learning","volume-title":"International Conference on Learning Representations","author":"Ghosh"},{"key":"ref9","article-title":"Rethinking goal-conditioned supervised learning and its connection to offline rl","volume-title":"International Conference on Learning Representations","author":"Yang"},{"key":"ref10","first-page":"1518","article-title":"Actionable models: Unsupervised offline reinforcement learning of robotic skills","volume-title":"International Conference on Machine Learning","author":"Chebotar"},{"key":"ref11","first-page":"310","article-title":"Offline goal-conditioned reinforcement learning via f-advantage regression","volume":"35","author":"Ma","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","article-title":"Distance weighted supervised learning for offline interaction data","author":"Hejna","year":"2023","journal-title":"arXiv preprint arXiv:2304.13774"},{"key":"ref13","first-page":"106","article-title":"Generalization with lossy affordances: Leveraging broad offline data for learning visuomotor tasks","volume-title":"Conference on Robot Learning","author":"Fang"},{"key":"ref14","first-page":"1401","article-title":"Learning goal-conditioned policies offline with self-supervised reward shaping","volume-title":"Conference on Robot Learning","author":"Mezghani"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref16","article-title":"Constrained Markov Decision Processes","volume-title":"PhD thesis, INRIA","author":"Altman","year":"1995"},{"issue":"1","key":"ref17","first-page":"6070","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2017","journal-title":"The Journal of Machine Learning Research"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20855"},{"key":"ref19","article-title":"Coptidice: Offline constrained reinforcement learning via stationary distribution correction estimation","volume-title":"International Conference on Learning Representations","author":"Lee"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013937"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981873"},{"key":"ref23","article-title":"Swapped goal-conditioned offline reinforcement learning","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv:2302.08865"},{"key":"ref24","first-page":"20035","article-title":"Hierarchical diffusion for offline decision making","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref25","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International Conference on machine learning","author":"Achiam"},{"key":"ref26","article-title":"Reward constrained policy optimization","volume-title":"International Conference on Learning Representations","author":"Tessler"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981831"},{"key":"ref28","article-title":"Safe offline reinforcement learning with real-time budget constraints","author":"Lin","year":"2023","journal-title":"arXiv preprint arXiv:2306.00603"},{"key":"ref29","first-page":"3703","article-title":"Batch policy learning under constraints","volume-title":"International Conference on Machine Learning","author":"Le"},{"key":"ref30","article-title":"Constrained decision transformer for offline safe reinforcement learning","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv:2302.07351"},{"key":"ref31","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv preprint arXiv:2005.01643"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref34","article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","author":"Peng","year":"2019","journal-title":"arXiv preprint arXiv:1910.00177"},{"key":"ref35","article-title":"Offline reinforcement learning with implicit q-learning","volume-title":"International Conference on Learning Representations","author":"Kostrikov"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref37","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume":"34","author":"Fujimoto","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref38","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"Plappert","year":"2018","journal-title":"arXiv preprint arXiv:1802.09464"},{"key":"ref39","article-title":"panda-gym: Open-source goal-conditioned environments for robotic learning","author":"Gallou\u00e9dec","year":"2021","journal-title":"arXiv preprint arXiv:2106.13687"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref41","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International Conference on machine learning","author":"Fujimoto"},{"key":"ref42","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref43","first-page":"9133","article-title":"Responsive safety in reinforcement learning by pid lagrangian methods","volume-title":"International Conference on Machine Learning","author":"Stooke"}],"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\/10610856.pdf?arnumber=10610856","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:58:02Z","timestamp":1723269482000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610856\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610856","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}