{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:04:10Z","timestamp":1774415050415,"version":"3.50.1"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2020YFA0711402"],"award-info":[{"award-number":["2020YFA0711402"]}]},{"name":"National Key Research and Development Program of China","award":["2021YFB2501104"],"award-info":[{"award-number":["2021YFB2501104"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/lra.2023.3333248","type":"journal-article","created":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T14:09:24Z","timestamp":1700057364000},"page":"491-498","source":"Crossref","is-referenced-by-count":8,"title":["Safe Reinforcement Learning With Dead-Ends Avoidance and Recovery"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8081-2079","authenticated-orcid":false,"given":"Xiao","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1301-8605","authenticated-orcid":false,"given":"Hai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0609-4226","authenticated-orcid":false,"given":"Hongtu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4815-8761","authenticated-orcid":false,"given":"Chang","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7135-272X","authenticated-orcid":false,"given":"Di","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0048-6974","authenticated-orcid":false,"given":"Chen","family":"Ye","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7864-3255","authenticated-orcid":false,"given":"Junqiao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.075"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/763"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref6","article-title":"Decoupling exploration and exploitation in reinforcement learning","volume-title":"Proc. Workshop Unsupervised Reinforcement Learn.","author":"Schfer","year":"2021"},{"key":"ref7","first-page":"1110","article-title":"Learning to walk in the real world with minimal human effort","volume-title":"Proc. Conf. Robot Learn.","author":"Ha","year":"2021"},{"key":"ref8","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam","year":"2017"},{"key":"ref9","article-title":"Projection-based constrained policy optimization","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Yang","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981030"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3063989"},{"key":"ref13","first-page":"9797","article-title":"Safe reinforcement learning in constrained Markov decision processes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wachi","year":"2020"},{"key":"ref14","article-title":"MESA: Offline meta-rl for safe adaptation and fault tolerance","author":"Luo","year":"2021"},{"key":"ref15","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref16","article-title":"Decoupled exploration and exploitation policies for sample-efficient reinforcement learning","author":"Whitney","year":"2021"},{"key":"ref17","article-title":"Learning to be safe: Deep RL with a safety critic","author":"Srinivasan","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981831"},{"key":"ref19","first-page":"1873","article-title":"Dead-ends and secure exploration in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fatemi","year":"2019"},{"key":"ref20","first-page":"4856","article-title":"Medical dead-ends and learning to identify high-risk states and treatments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fatemi","year":"2021"},{"key":"ref21","article-title":"Risk sensitive dead-end identification in safety-critical offline reinforcement learning","author":"Killian","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref22","first-page":"13859","article-title":"Safe reinforcement learning by imagining the near future","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Thomas","year":"2021"},{"key":"ref23","article-title":"When to trust your model: Model-based policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Janner","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref26","article-title":"Offline reinforcement learning with implicit Q-learning","author":"Kostrikov","year":"2021","journal-title":"Deep RL Workshop NeurIPS"},{"key":"ref27","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref28","article-title":"Benchmarking safe exploration in deep reinforcement learning","author":"Ray","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17272"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10320104\/10319093.pdf?arnumber=10319093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T17:10:24Z","timestamp":1761066624000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10319093\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":29,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3333248","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}