{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T20:13:54Z","timestamp":1784837634290,"version":"3.55.0"},"reference-count":30,"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\/icra57147.2024.10610510","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"10503-10509","source":"Crossref","is-referenced-by-count":4,"title":["Synthesis of Temporally-Robust Policies for Signal Temporal Logic Tasks using Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Siqi","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Automation and Key Laboratory of System Control and Information Processing,Shanghai,China,200240"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoyuan","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Automation and Key Laboratory of System Control and Information Processing,Shanghai,China,200240"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Yin","sequence":"additional","affiliation":[{"name":"Macau University of Science and Technology,Institute of Systems Engineering,Taipa,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Yin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Automation and Key Laboratory of System Control and Information Processing,Shanghai,China,200240"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30206-3_12"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-39799-8_19"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2023.111445"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068114"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2018.05.011"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3069943"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3359986.3361203"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15297-9_9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2022.3209928"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3550072"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3501710.3519504"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10384038"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10703-016-0261-8"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21668-3_21"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2606"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039363"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2022.3172857"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146951"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383500"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2018.2853182"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2020.3014602"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483028"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7799279"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3302504.3313355"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683444"},{"key":"ref26","first-page":"308","article-title":"Tractable reinforcement learning of signal temporal logic objectives","author":"Venkataraman","year":"2020","journal-title":"Learning for Dynamics and Control"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3218216"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683477"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9992914"},{"key":"ref30","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"}],"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\/10610510.pdf?arnumber=10610510","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:50:17Z","timestamp":1723269017000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610510\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610510","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}