{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T20:09:24Z","timestamp":1730232564872,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T00:00:00Z","timestamp":1718668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T00:00:00Z","timestamp":1718668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,18]]},"DOI":"10.1109\/icca62789.2024.10591902","type":"proceedings-article","created":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T17:19:13Z","timestamp":1721927953000},"page":"478-483","source":"Crossref","is-referenced-by-count":0,"title":["Formal Control Synthesis via Safe Reinforcement Learning Under Real-Time Specifications"],"prefix":"10.1109","author":[{"given":"Peng","family":"Lv","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Key Laboratory of System Control and Information Processing,Department of Automation,Shanghai,China,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangqing","family":"Luo","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Key Laboratory of System Control and Information Processing,Department of Automation,Shanghai,China,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhou","family":"He","sequence":"additional","affiliation":[{"name":"School of Electrical and Control Engineering, Shaanxi University of Science and Technology,Xi'an,China,710021"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianwei","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Key Laboratory of System Control and Information Processing,Department of Automation,Shanghai,China,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Yin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Key Laboratory of System Control and Information Processing,Department of Automation,Shanghai,China,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"issue":"1","key":"ref2","first-page":"1437","article-title":"A comprehensive survey on safe rein-forcement learning","volume":"16","author":"Garcia","year":"2015","journal-title":"Journal of Machine Learning Research"},{"journal-title":"Principles of model checking","year":"2008","author":"Baier","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2024.100940"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/227595.227602"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-247-2.50017-6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2484359"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2389313"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039527"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206234"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/CCC52363.2021.9549746"},{"journal-title":"IEEE International Conference on Robotics and Automation (ICRA)","article-title":"Synthesis of temporally-robust policies for signal temporal logic tasks using reinforcement learning","author":"Wang","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-46681-0_51"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/0304-3975(94)90010-8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963221"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15297-9_13"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36387-4_2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-59042-0_76"},{"issue":"268","key":"ref20","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"}],"event":{"name":"2024 IEEE 18th International Conference on Control & Automation (ICCA)","start":{"date-parts":[[2024,6,18]]},"location":"Reykjav\u00edk, Iceland","end":{"date-parts":[[2024,6,21]]}},"container-title":["2024 IEEE 18th International Conference on Control & Automation (ICCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10591777\/10591797\/10591902.pdf?arnumber=10591902","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T05:23:58Z","timestamp":1721971438000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10591902\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,18]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icca62789.2024.10591902","relation":{},"subject":[],"published":{"date-parts":[[2024,6,18]]}}}