{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T18:04:42Z","timestamp":1786039482191,"version":"3.56.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Under Secretary of Defense for Research and Engineering"},{"name":"Air Force Contract","award":["FA8702-15-D-0001"],"award-info":[{"award-number":["FA8702-15-D-0001"]}]},{"DOI":"10.13039\/100008234","name":"Lehigh University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008234","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF","award":["IIS-2024606"],"award-info":[{"award-number":["IIS-2024606"]}]},{"DOI":"10.13039\/100007161","name":"Boston University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007161","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1109\/lra.2023.3246844","type":"journal-article","created":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T23:43:30Z","timestamp":1676936610000},"page":"2158-2165","source":"Crossref","is-referenced-by-count":30,"title":["Overcoming Exploration: Deep Reinforcement Learning for Continuous Control in Cluttered Environments From Temporal Logic Specifications"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2967-2703","authenticated-orcid":false,"given":"Mingyu","family":"Cai","sequence":"first","affiliation":[{"name":"Mechanical Engineering, Lehigh University, Bethlehem, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erfan","family":"Aasi","sequence":"additional","affiliation":[{"name":"Mechanical Engineering Department, Boston University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7141-2657","authenticated-orcid":false,"given":"Calin","family":"Belta","sequence":"additional","affiliation":[{"name":"Mechanical Engineering Department, Boston University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1132-1462","authenticated-orcid":false,"given":"Cristian-Ioan","family":"Vasile","sequence":"additional","affiliation":[{"name":"Mechanical Engineering, Lehigh University, Bethlehem, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref3","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref4","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2016","journal-title":"Proc. Int. Conf. Learn. Representation"},{"key":"ref5","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"OpenAI"},{"key":"ref6","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Lowe","year":"2017"},{"key":"ref7","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref10","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017"},{"key":"ref11","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/02783640122067453"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364904045481"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0967-0661(02)00186-7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2668380"},{"key":"ref17","first-page":"1724","article-title":"Safe nonlinear control using robust neural lyapunov-barrier functions","volume-title":"Proc. Conf. Robot Learn.","author":"Dawson"},{"key":"ref18","volume-title":"Principles of Model Checking","author":"Baier","year":"2008"},{"key":"ref19","first-page":"2107","article-title":"Using reward machines for high-level task specification and decomposition in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Icarte","year":"2018"},{"key":"ref20","article-title":"Deepsynth: Program synthesis for automatic task segmentation in deep reinforcement learning","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Hasanbeig","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v30i1.6756"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aay6276"},{"key":"ref23","first-page":"10497","article-title":"LTL2Action: Generalizing LTL instructions for multi-task RL","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Vaezipoor","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12440"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3101544"},{"key":"ref26","article-title":"Safety-critical modular deep reinforcement learning with temporal logic through Gaussian processes and control barrier functions","author":"Cai","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57628-8_1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-41540-6_17"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920918919"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920913922"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.3031254"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3061983"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/504729.504754"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2007.914952"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2023.3246844"},{"key":"ref36","first-page":"322","article-title":"An automata-theoretic approach to automatic program verification","volume-title":"Proc. First Symp. Log. Comput. Sci.","author":"Vardi","year":"1986"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44585-4_6"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3141657"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/10049284\/10049066-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10049284\/10049066.pdf?arnumber=10049066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T16:38:52Z","timestamp":1707842332000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10049066\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4]]},"references-count":39,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3246844","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4]]}}}