{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T18:54:09Z","timestamp":1770749649505,"version":"3.50.0"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"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","award":["U2013601"],"award-info":[{"award-number":["U2013601"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62173314"],"award-info":[{"award-number":["62173314"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tnnls.2023.3339885","type":"journal-article","created":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T14:46:14Z","timestamp":1702910774000},"page":"3870-3877","source":"Crossref","is-referenced-by-count":2,"title":["Data-Driven Safe Policy Optimization for Black-Box Dynamical Systems With Temporal Logic Specifications"],"prefix":"10.1109","volume":"36","author":[{"given":"Chenlin","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, Anhui, China"}]},{"given":"Shijun","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3132-2809","authenticated-orcid":false,"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6540-8451","authenticated-orcid":false,"given":"Ziyang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6985-240X","authenticated-orcid":false,"given":"Shaochen","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2069-9544","authenticated-orcid":false,"given":"Zhen","family":"Kan","sequence":"additional","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, Anhui, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"27580","article-title":"Online and offline reinforcement learning by planning with a learned model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Schrittwieser"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3138704"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.04.001"},{"key":"ref4","first-page":"13644","article-title":"Constrained variational policy optimization for safe reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref5","article-title":"Learnings options end-to-end for continuous action tasks","author":"Klissarov","year":"2017","journal-title":"arXiv:1712.00004"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2638961"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3033324"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.3002762"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3144135"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2967871"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561253"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341190"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294485"},{"key":"ref16","article-title":"Learning safe multi-agent control with decentralized neural barrier certificates","author":"Qin","year":"2021","journal-title":"arXiv:2101.05436"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303785"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142743"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3238656"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2654539"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084685"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-28582-4"},{"key":"ref23","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Achiam"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-012-9989-5"},{"key":"ref25","first-page":"1","article-title":"Projection-based constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref26","first-page":"11795","article-title":"Accelerating safe reinforcement learning with constraint-mismatched baseline policies","volume-title":"Proc. Mach. Learn. Res.","author":"Yang"},{"key":"ref27","article-title":"Reward constrained policy optimization","author":"Tessler","year":"2018","journal-title":"arXiv:1805.11074"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3006967"},{"key":"ref29","first-page":"452","article-title":"Teaching multiple tasks to an RL agent using LTL","volume-title":"Proc. Int. Joint Conf. Auton. Agents Multiagent Syst.","author":"Toro Icarte"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196796"},{"key":"ref31","first-page":"10497","article-title":"LTL2Action: Generalizing LTL instructions for multi-task RL","volume-title":"Proc. Int. Conf. Machin. Learn.","author":"Vaezipoor"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aay6276"},{"key":"ref33","article-title":"Safety-critical learning of robot control with temporal logic specifications","author":"Cai","year":"2021","journal-title":"arXiv:2109.02791"},{"key":"ref34","volume-title":"Principles of Model Checking","author":"Baier","year":"2008"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44585-4_6"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejcon.2021.01.008"},{"key":"ref37","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref38","first-page":"25636","article-title":"Reachability constrained reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10877690\/10363340.pdf?arnumber=10363340","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:38:51Z","timestamp":1764959931000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10363340\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":38,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3339885","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}