{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T06:25:23Z","timestamp":1782887123956,"version":"3.54.5"},"reference-count":20,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62173226"],"award-info":[{"award-number":["62173226"]}],"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":["62061136004"],"award-info":[{"award-number":["62061136004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Control Syst. Lett."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/lcsys.2024.3397844","type":"journal-article","created":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T17:41:41Z","timestamp":1715103701000},"page":"616-621","source":"Crossref","is-referenced-by-count":5,"title":["Tractable Reinforcement Learning for Signal Temporal Logic Tasks With Counterfactual Experience Replay"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3186-7785","authenticated-orcid":false,"given":"Siqi","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Automation and the Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9823-9209","authenticated-orcid":false,"given":"Xunyuan","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Chemistry, Chemical Engineering and Biotechnology, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3427-2912","authenticated-orcid":false,"given":"Shaoyuan","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Automation and the Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1944-1570","authenticated-orcid":false,"given":"Xiang","family":"Yin","sequence":"additional","affiliation":[{"name":"Department of Automation and the Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3359986.3361203"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2461328.2461337"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068114"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.103998"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039363"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2022.3172857"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146951"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2018.2853182"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2020.3014602"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483028"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7799279"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8618746"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968254"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683444"},{"key":"ref15","first-page":"308","article-title":"Tractable reinforcement learning of signal temporal logic objectives","volume-title":"Proc. Learn. Dyn. Control","author":"Venkataraman"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3218216"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26764"},{"key":"ref18","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref19","article-title":"Eventual discounting temporal logic counterfactual experience replay","author":"Voloshin","year":"2023","journal-title":"arXiv:2303.02135"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/465"}],"container-title":["IEEE Control Systems Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782633\/10411713\/10522501.pdf?arnumber=10522501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T17:41:46Z","timestamp":1729791706000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10522501\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/lcsys.2024.3397844","relation":{},"ISSN":["2475-1456"],"issn-type":[{"value":"2475-1456","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}