{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:54:57Z","timestamp":1781798097410,"version":"3.54.5"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801338","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"12378-12385","source":"Crossref","is-referenced-by-count":1,"title":["Safe Reinforcement Learning via Hierarchical Adaptive Chance-Constraint Safeguards"],"prefix":"10.1109","author":[{"given":"Zhaorun","family":"Chen","sequence":"first","affiliation":[{"name":"University of Chicago,Department of Computer Science,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuokai","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Chicago,Department of Computer Science,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tairan","family":"He","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Robotics Institute,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binhao","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Mechanical Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuhao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Mechanical Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Gong","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Mechanical Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengliang","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Mechanical Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International conference on machine learning","author":"Achiam"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63735-3_2"},{"key":"ref5","volume-title":"Reinforcement learning and optimal control","author":"Bertsekas","year":"2019"},{"key":"ref6","article-title":"Conservative safety critics for exploration","author":"Bharadhwaj","year":"2020"},{"key":"ref7","article-title":"Value constrained model-free continuous control","author":"Bohez","year":"2019"},{"key":"ref8","article-title":"A primal-dual approach to constrained markov decision processes","author":"Chen","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref10","article-title":"A lyapunov-based approach to safe reinforcement learning","volume":"31","author":"Chow","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Safe exploration in continuous action spaces","author":"Dalal","year":"2018"},{"key":"ref12","article-title":"Dc3: A learning method for optimization with hard constraints","author":"Donti","year":"2021"},{"key":"ref13","volume-title":"Markov processes: characterization and convergence","author":"Ethier","year":"2009"},{"key":"ref14","article-title":"Leave no trace: Learning to reset for safe and autonomous reinforcement learning","author":"Eysenbach","year":"2017"},{"key":"ref15","article-title":"Shieldnn: A provably safe nn filter for unsafe nn controllers","author":"Ferlez","year":"2020"},{"key":"ref16","article-title":"Iterative reachability estimation for safe reinforcement learning","volume":"36","author":"Ganai","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827264"},{"issue":"1","key":"ref18","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u0131a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26734"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9992692"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619572"},{"key":"ref23","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":"ref24","article-title":"Accelerated primal-dual policy optimization for safe reinforcement learning","author":"Liang","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/614"},{"key":"ref27","article-title":"Learn zero-constraint-violation policy in model-free constrained reinforcement learning","author":"Ma","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.361"},{"issue":"268","key":"ref29","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"ref30","first-page":"2","article-title":"Benchmarking safe exploration in deep reinforcement learning","volume":"7","author":"Ray","year":"2019"},{"key":"ref31","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning","author":"Schulman"},{"key":"ref32","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3192205"},{"key":"ref34","article-title":"Learning to be safe: Deep rl with a safety critic","author":"Srinivasan","year":"2020"},{"key":"ref35","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref36","article-title":"Reward constrained policy optimization","author":"Tessler","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2976272"},{"key":"ref39","first-page":"10630","article-title":"Safe reinforcement learning using advantage-based intervention","volume-title":"International Conference on Machine Learning","author":"Wagener"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.23919\/ACC53348.2022.9867675"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029720"},{"key":"ref42","article-title":"Constrained cross-entropy method for safe reinforcement learning","volume":"31","author":"Wen","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26786"},{"key":"ref44","first-page":"15338","article-title":"First order constrained optimization in policy space","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CYBER46603.2019.9066510"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/763"},{"key":"ref47","article-title":"Model-free safe control for zero-violation reinforcement learning","volume-title":"5th Annual Conference on Robot Learning","author":"Zhao"},{"key":"ref48","first-page":"783","article-title":"Probabilistic safeguard for reinforcement learning using safety index guided gaussian process models","volume-title":"Learning for Dynamics and Control Conference","author":"Zhao"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10801338.pdf?arnumber=10801338","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:27:55Z","timestamp":1735198075000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801338\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801338","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}