{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,27]],"date-time":"2025-04-27T04:01:28Z","timestamp":1745726488190,"version":"3.40.4"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["#2231257"],"award-info":[{"award-number":["#2231257"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tac.2024.3484290","type":"journal-article","created":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T17:27:25Z","timestamp":1729531645000},"page":"2873-2888","source":"Crossref","is-referenced-by-count":0,"title":["Sample-Efficient Reinforcement Learning With Temporal Logic Objectives: Leveraging the Task Specification to Guide Exploration"],"prefix":"10.1109","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0257-7378","authenticated-orcid":false,"given":"Yiannis","family":"Kantaros","sequence":"first","affiliation":[{"name":"Department of Electrical and Systems Engineering, Washington University in St. Louis, St. Louis, MO, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0481-8697","authenticated-orcid":false,"given":"Jun","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Systems Engineering, Washington University in St. Louis, St. Louis, MO, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref2","first-page":"13","article-title":"Reinforcement learning and the reward engineering principle","volume-title":"Proc. AAAI Spring Symp. Ser.","author":"Dewey","year":"2014"},{"volume-title":"Principles of Model Checking","year":"2008","author":"Baier","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915581505"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17462-0_27"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3302509.3311053"},{"article-title":"Reinforcement learning with probabilistic guarantees for autonomous driving","year":"2019","author":"Bouton","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9028919"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196796"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3006967"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS48487.2020.00017"},{"key":"ref12","first-page":"10026","article-title":"Compositional reinforcement learning from logical specifications","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Jothimurugan","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16336-4_11"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103949"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2024.3390848"},{"key":"ref16","first-page":"428","article-title":"On the uniqueness of solution for the Bellman equation of LTL objectives","volume-title":"Proc. 6th Annu. Learn. Dyn. Control Conf.","author":"Xuan","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16935"},{"key":"ref18","first-page":"2107","article-title":"Using reward machines for high-level task specification and decomposition in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Icarte","year":"2018"},{"key":"ref19","first-page":"6708","article-title":"On efficiency in hierarchical reinforcement learning","volume":"33","author":"Wen","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12440"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/ACC55779.2023.10156544"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383559"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13326"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3246844"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref27","first-page":"5094","article-title":"Boltzmann exploration done right","volume":"30","author":"Cesa-Bianchi","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"article-title":"UCB exploration via q-ensembles","year":"2017","author":"Chen","key":"ref28"},{"article-title":"A survey of exploration methods in reinforcement learning","year":"2021","author":"Amin","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.039"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11936-6_8"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2010.03.007"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920913922"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3144073"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.11.030"},{"key":"ref36","first-page":"1587","article-title":"Optimal policy generation for partially satisfiable co-safe LTL specifications","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Lacerda","year":"2015"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981759"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-41540-6_17"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3138704"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2007.914952"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9519-z"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989036"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2626400"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110228"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2799561"},{"volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","year":"2014","author":"Puterman","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2298143"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.03.027"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/9\/10977569\/10726789-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9\/10977569\/10726789.pdf?arnumber=10726789","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T04:50:25Z","timestamp":1745643025000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10726789\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":49,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tac.2024.3484290","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"type":"print","value":"0018-9286"},{"type":"electronic","value":"1558-2523"},{"type":"electronic","value":"2334-3303"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}