{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T23:31:54Z","timestamp":1769815914291,"version":"3.49.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/cdc40024.2019.9028919","type":"proceedings-article","created":{"date-parts":[[2020,3,13]],"date-time":"2020-03-13T00:43:11Z","timestamp":1584060191000},"page":"5338-5343","source":"Crossref","is-referenced-by-count":79,"title":["Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees"],"prefix":"10.1109","author":[{"given":"M.","family":"Hasanbeig","sequence":"first","affiliation":[]},{"given":"Y.","family":"Kantaros","sequence":"additional","affiliation":[]},{"given":"A.","family":"Abate","sequence":"additional","affiliation":[]},{"given":"D.","family":"Kroening","sequence":"additional","affiliation":[]},{"given":"G. J.","family":"Pappas","sequence":"additional","affiliation":[]},{"given":"I.","family":"Lee","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.039"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11936-6_8"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623517"},{"key":"ref13","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915581505"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3302509.3311053"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17462-0_28"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12107","article-title":"Safe reinforcement learning via formal methods: Toward safe control through proof and learning","author":"fulton","year":"2018","journal-title":"AAAI"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10817-008-9103-8"},{"key":"ref19","article-title":"Logically-constrained reinforcement learning","author":"hasanbeig","year":"2018"},{"key":"ref28","first-page":"585","article-title":"PRISM 4.0: Verification of probabilistic real-time systems","author":"kwiatkowska","year":"2011","journal-title":"CAV"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ic.2016.11.006"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.039"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2799561"},{"key":"ref6","author":"clarke","year":"2018","journal-title":"Model checking"},{"key":"ref5","author":"baier","year":"2008","journal-title":"Principles of Model Checking"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/963927.963928"},{"key":"ref7","first-page":"312","article-title":"Limit-deterministic Büchi automata for linear temporal logic","author":"sickert","year":"2016","journal-title":"CAV"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2298143"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46520-3_9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6426174"},{"key":"ref20","first-page":"2012","article-title":"Logically-constrained neural fitted Q-iteration","author":"hasanbeig","year":"2019","journal-title":"AAMAS"},{"key":"ref22","year":"0"},{"key":"ref21","article-title":"Omega-regular objectives in model-free reinforcement learning","author":"hahn","year":"2018","journal-title":"TACAS"},{"key":"ref24","author":"puterman","year":"2014","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1977.32"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3166\/ejc.16.624-641"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.03.027"}],"event":{"name":"2019 IEEE 58th Conference on Decision and Control (CDC)","location":"Nice, France","start":{"date-parts":[[2019,12,11]]},"end":{"date-parts":[[2019,12,13]]}},"container-title":["2019 IEEE 58th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8977134\/9028853\/09028919.pdf?arnumber=9028919","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,28]],"date-time":"2023-09-28T11:01:41Z","timestamp":1695898901000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9028919\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/cdc40024.2019.9028919","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}