{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T18:45:43Z","timestamp":1770749143117,"version":"3.50.0"},"reference-count":27,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"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":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1109\/lra.2023.3313969","type":"journal-article","created":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T18:28:47Z","timestamp":1695148127000},"page":"7010-7017","source":"Crossref","is-referenced-by-count":3,"title":["Reinforcement Learning of Action and Query Policies With LTL Instructions Under Uncertain Event Detector"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4030-5142","authenticated-orcid":false,"given":"Wataru","family":"Hatanaka","sequence":"first","affiliation":[{"name":"Digital Strategy Division, RICOH Company, Ltd., Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryota","family":"Yamashina","sequence":"additional","affiliation":[{"name":"Digital Strategy Division, RICOH Company, Ltd., Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3545-4814","authenticated-orcid":false,"given":"Takamitsu","family":"Matsubara","sequence":"additional","affiliation":[{"name":"Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST), Nara, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1977.32"},{"key":"ref2","first-page":"452","article-title":"Teaching multiple tasks to an RL agent using LTL","volume-title":"Proc. Int. Conf. Auton. Agents MultiAgent Syst.","author":"Icarte","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/840"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561989"},{"key":"ref5","article-title":"Systematic generalisation through task temporal logic and deep reinforcement learning","author":"Len","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341325"},{"key":"ref7","first-page":"10497","article-title":"LTL2Action: Generalizing LTL instructions for multi-task RL","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Vaezipoor","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2977217"},{"key":"ref9","first-page":"3484","article-title":"Task-oriented active perception and planning in environments with partially known semantics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ghasemi","year":"2020"},{"key":"ref10","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":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9028919"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3032845"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3144073"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3101544"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2014.6858909"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i06.6563"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3470453"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197297"},{"key":"ref19","article-title":"Noisy symbolic abstractions for deep RL: A case study with reward machines","author":"Li","year":"2022"},{"issue":"3","key":"ref20","first-page":"291","article-title":"Model checking of safety properties","volume-title":"Formal Methods Syst. Des.","volume":"19","author":"Kupferman","year":"2001"},{"key":"ref21","volume-title":"Principles of Model Checking","author":"Baier","year":"2008"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00071-5"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"ref24","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref25","article-title":"Isaac Gym: High performance GPU-based physics simulation for robot learning","author":"Makoviychuk","year":"2021"},{"key":"ref26","article-title":"A composable specification language for reinforcement learning tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jothimurugan","year":"2019"},{"key":"ref27","first-page":"7553","article-title":"Maximum entropy-regularized multi-goal reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhao","year":"2019"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10254630\/10246967.pdf?arnumber=10246967","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T01:03:48Z","timestamp":1709341428000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10246967\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":27,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3313969","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}