{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T14:30:03Z","timestamp":1771943403512,"version":"3.50.1"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"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","award":["U2013601"],"award-info":[{"award-number":["U2013601"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1109\/lra.2021.3101544","type":"journal-article","created":{"date-parts":[[2021,8,4]],"date-time":"2021-08-04T20:07:25Z","timestamp":1628107645000},"page":"7973-7980","source":"Crossref","is-referenced-by-count":68,"title":["Modular Deep Reinforcement Learning for Continuous Motion Planning With Temporal Logic"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2967-2703","authenticated-orcid":false,"given":"Mingyu","family":"Cai","sequence":"first","affiliation":[]},{"given":"Mohammadhosein","family":"Hasanbeig","sequence":"additional","affiliation":[]},{"given":"Shaoping","family":"Xiao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5627-9093","authenticated-orcid":false,"given":"Alessandro","family":"Abate","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2069-9544","authenticated-orcid":false,"given":"Zhen","family":"Kan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref32","first-page":"543","article-title":"Owl: A library for $\\omega$-words, automata, and LTL","author":"kret\u00ednsk\u00fd","year":"2018","journal-title":"Proc Autom Tech Verif Anal"},{"key":"ref31","volume":"1","author":"durrett","year":"1999","journal-title":"Essentials of Stochastic Processes"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017984413808"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915581505"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3006967"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9028919"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17462-0_27"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196796"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.2980552"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7799279"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref18","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref19","first-page":"312","article-title":"Limit-deterministic Büchi automata for linear temporal logic","author":"sickert","year":"2016","journal-title":"Proc Int Conf Comput Aided Verif"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920918919"},{"key":"ref27","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"1999","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914546174"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919856695"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1109\/LRA.2021.3101544","article-title":"Modular deep reinforcement learning for continuous motion planning with temporal logic","author":"cai","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2298143"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623517"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2015.2454299"},{"key":"ref2","author":"baier","year":"2008","journal-title":"Principles of Model Checking"},{"key":"ref9","article-title":"Probably approximately correct MDP learning and control with temporal logic constraints","year":"0"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","first-page":"2107","article-title":"Using reward machines for high-level task specification and decomposition in reinforcement learning","author":"icarte","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aay6276"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/840"},{"key":"ref24","article-title":"Modular deep reinforcement learning with temporal logic specifications","author":"yuan","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3302509.3311053"},{"key":"ref26","article-title":"Continuous motion planning with temporal logic specifications using deep neural networks","author":"wang","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57628-8_1"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9475905\/09506925.pdf?arnumber=9506925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T15:06:49Z","timestamp":1673017609000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9506925\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":32,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3101544","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10]]}}}