{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T22:55:27Z","timestamp":1740178527636,"version":"3.37.3"},"reference-count":18,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency (JST)-ERATO HASUO Project, Japan","doi-asserted-by":"publisher","award":["JPMJER1603"],"award-info":[{"award-number":["JPMJER1603"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]},{"name":"JST CREST, Japan","award":["JPMJCR2012"],"award-info":[{"award-number":["JPMJCR2012"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Control Syst. Lett."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/lcsys.2022.3169982","type":"journal-article","created":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T21:10:16Z","timestamp":1650921016000},"page":"2557-2562","source":"Crossref","is-referenced-by-count":0,"title":["Learning-Based Bounded Synthesis for Semi-MDPs With LTL Specifications"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9864-4506","authenticated-orcid":false,"given":"Ryohei","family":"Oura","sequence":"first","affiliation":[{"name":"Graduate School of Engineering Science, Osaka University, Toyonaka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4009-270X","authenticated-orcid":false,"given":"Toshimitsu","family":"Ushio","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering Science, Osaka University, Toyonaka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Applied Probability Models with Optimization Applications","year":"2013","author":"ross","key":"ref10"},{"key":"ref11","first-page":"393","article-title":"Reinforcement learning methods for continuous-time Markov decision","volume":"7","author":"bradtke","year":"1994","journal-title":"Proc 7th Adv Neural Inf Process Syst"},{"key":"ref12","first-page":"3349","article-title":"Semi-Markov reinforcement learning for stochastic resource collection","author":"schmoll","year":"2021","journal-title":"Proc 29th Int Conf Int Joint Conf Artif Intell"},{"key":"ref13","article-title":"A learning based optimal human robot collaboration with linear temporal logic constraints","author":"wu","year":"2017","journal-title":"arXiv 1706 00007"},{"key":"ref14","first-page":"3630","article-title":"Probably approximately correct learning in stochastic games with temporal logic specifications","author":"wen","year":"2016","journal-title":"Proc Int Joint Artif Intell Conf"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.039"},{"journal-title":"Pattern Recognition and Machine Learning","year":"2006","author":"bishop","key":"ref16"},{"key":"ref17","article-title":"A detailed treatment of Doob’s theorem","author":"miller","year":"2018","journal-title":"arXiv 1801 03122"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"ref18"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17462-0_27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196796"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206234"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.2980552"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10703-011-0115-3"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aay6276"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039527"},{"journal-title":"Principles of Model Checking","year":"2008","author":"baier","key":"ref1"},{"key":"ref9","article-title":"Bounded synthesis and reinforcement learning of supervisors for stochastic discrete event systems with LTL specifications","author":"oura","year":"2021","journal-title":"arXiv 2105 03081"}],"container-title":["IEEE Control Systems Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782633\/9462165\/09762370.pdf?arnumber=9762370","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,6]],"date-time":"2022-06-06T20:10:41Z","timestamp":1654546241000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9762370\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/lcsys.2022.3169982","relation":{},"ISSN":["2475-1456"],"issn-type":[{"type":"electronic","value":"2475-1456"}],"subject":[],"published":{"date-parts":[[2022]]}}}