{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T00:43:34Z","timestamp":1753922614095,"version":"3.37.3"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561903","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"806-812","source":"Crossref","is-referenced-by-count":17,"title":["Reinforcement Learning Based Temporal Logic Control with Maximum Probabilistic Satisfaction"],"prefix":"10.1109","author":[{"given":"Mingyu","family":"Cai","sequence":"first","affiliation":[]},{"given":"Shaoping","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Baoluo","family":"Li","sequence":"additional","affiliation":[]},{"given":"Zhiliang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Zhen","family":"Kan","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":"10.1177\/0278364915581505"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aay6276"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3302509.3311053"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3006967"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17462-0_27"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196796"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9028919"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.2980552"},{"article-title":"Continuous motion planning with temporal logic specifications using deep neural networks","year":"2020","author":"wang","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2298143"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01090-4_34"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920913922"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919856695"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2799561"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"article-title":"Optimal probabilistic motion planning with partially infeasible LTL constraints","year":"2020","author":"cai","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3032845"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623517"},{"journal-title":"Principles of Model Checking","year":"2008","author":"baier","key":"ref1"},{"key":"ref20","article-title":"DeepSynth: Program synthesis for automatic task segmentation in deep reinforcement learning","author":"hasanbeig","year":"2021","journal-title":"AAAI Conf Artif Intell"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/840"},{"key":"ref21","first-page":"2107","article-title":"Using reward machines for high-level task specification and decomposition in reinforcement learning","author":"icarte","year":"2018","journal-title":"Int Conf Mach Learn"},{"article-title":"Certified reinforcement learning with logic guidance","year":"2019","author":"hasanbeig","key":"ref24"},{"key":"ref23","first-page":"312","article-title":"Limit-deterministic Büchi automata for linear temporal logic","author":"sickert","year":"2016","journal-title":"Int Conf Comput Aided Verif"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017984413808"},{"article-title":"Reinforcement learning based temporal logic control with maximum probabilistic satisfaction","year":"2020","author":"cai","key":"ref25"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2021,5,30]]},"location":"Xi'an, China","end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561903.pdf?arnumber=9561903","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:47:23Z","timestamp":1652197643000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561903\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561903","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}