{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:38:24Z","timestamp":1759333104542,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"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":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9636598","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T20:45:38Z","timestamp":1639687538000},"page":"6531-6537","source":"Crossref","is-referenced-by-count":7,"title":["Probabilistically Guaranteed Satisfaction of Temporal Logic Constraints During Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Derya","family":"Aksaray","sequence":"first","affiliation":[]},{"given":"Yasin","family":"Yazicioglu","sequence":"additional","affiliation":[]},{"given":"Ahmet Semi","family":"Asarkaya","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3015928"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29694-9_9"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-63010-4_6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1023\/B:MACH.0000039779.47329.3a"},{"key":"ref14","article-title":"Exploration-exploitation in constrained mdps","author":"efroni","year":"2020","journal-title":"ICML Workshop on Theoretical Foundations of Reinforcement Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2876389"},{"key":"ref16","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc?a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref17","first-page":"3","article-title":"Simple on-the-fly automatic verification of linear temporal logic","author":"gerth","year":"1995","journal-title":"Conference on Protocol Specification Testing and Verification"},{"key":"ref18","first-page":"483","author":"hasanbeig","year":"2020","journal-title":"Cautious reinforcement learning with logical constraints"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.entcs.2015.10.009"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"article-title":"Probabilistically guar-anteed satisfaction of temporal logic constraints during reinforcement learning","year":"2021","author":"aksaray","key":"ref4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2017.07.012"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487481"},{"journal-title":"Principles of Model Checking","year":"2008","author":"baier","key":"ref6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2016.2518083"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11797","article-title":"Safe reinforcement learning via shielding","volume":"32","author":"alshiekh","year":"2018","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8430795"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2019.12.156"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7799279"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196796"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102352"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920913922"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341624"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2009.2030225"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039527"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914537008"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2461328.2461372"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2021,9,27]]},"location":"Prague, Czech Republic","end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09636598.pdf?arnumber=9636598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T22:38:12Z","timestamp":1674081492000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636598\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636598","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}