{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:28:11Z","timestamp":1782847691363,"version":"3.54.5"},"reference-count":16,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JST-ERATO HASUO Project","award":["JPMJER1603, Japan"],"award-info":[{"award-number":["JPMJER1603, Japan"]}]},{"name":"JST-Mirai Program","award":["JPMJMI18B4, Japan"],"award-info":[{"award-number":["JPMJMI18B4, Japan"]}]},{"DOI":"10.13039\/501100001691","name":"Grant-in-Aid for Japan Society for the Promotion of Science Research Fellow","doi-asserted-by":"publisher","award":["JP19J13487"],"award-info":[{"award-number":["JP19J13487"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Control Syst. Lett."],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1109\/lcsys.2020.2980552","type":"journal-article","created":{"date-parts":[[2020,3,13]],"date-time":"2020-03-13T20:32:05Z","timestamp":1584131525000},"page":"761-766","source":"Crossref","is-referenced-by-count":23,"title":["Reinforcement Learning of Control Policy for Linear Temporal Logic Specifications Using Limit-Deterministic Generalized B\u00fcchi Automata"],"prefix":"10.1109","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9864-4506","authenticated-orcid":false,"given":"Ryohei","family":"Oura","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7997-1237","authenticated-orcid":false,"given":"Ami","family":"Sakakibara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4009-270X","authenticated-orcid":false,"given":"Toshimitsu","family":"Ushio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9028919"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17462-0_27"},{"key":"ref12","article-title":"Control synthesis from linear temporal logic specifications using model-free reinforcement learning","author":"bozkurt","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-3615-7"},{"key":"ref14","author":"breuer","year":"2019","journal-title":"Introduction to Stochastic Processes"},{"key":"ref15","author":"ross","year":"1996","journal-title":"Stochastic Processes"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007678930559"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50763-7"},{"key":"ref3","author":"baier","year":"2008","journal-title":"Principles of Model Checking"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3302509.3311053"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039527"},{"key":"ref8","first-page":"312","article-title":"Limit-deterministic B’´uchi automata for linear temporal logic","author":"sickert","year":"2016","journal-title":"Proc Int Conf Comput -Aided"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aay6276"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref9","article-title":"Logically-constrained reinforcement learning","author":"hasanbeig","year":"2018"}],"container-title":["IEEE Control Systems Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782633\/8995821\/09035633.pdf?arnumber=9035633","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,18]],"date-time":"2022-10-18T20:04:58Z","timestamp":1666123498000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9035633\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":16,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lcsys.2020.2980552","relation":{},"ISSN":["2475-1456"],"issn-type":[{"value":"2475-1456","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7]]}}}