{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:38:57Z","timestamp":1759333137249,"version":"3.37.3"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000185","name":"DARPA","doi-asserted-by":"publisher","award":["HR0011-21-2-0015"],"award-info":[{"award-number":["HR0011-21-2-0015"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10342259","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"8680-8686","source":"Crossref","is-referenced-by-count":1,"title":["Reinforcement Learning Under Probabilistic Spatio-Temporal Constraints with Time Windows"],"prefix":"10.1109","author":[{"given":"Xiaoshan","family":"Lin","sequence":"first","affiliation":[{"name":"University of Minnesota,Department of Aerospace Engineering and Mechanics,Minneapolis,MN,55455"}]},{"given":"Abbasali","family":"Koochakzadeh","sequence":"additional","affiliation":[{"name":"Purdue University,Department of Electrical and Computer Engineering,West Lafayette,IN,47907"}]},{"given":"Yasin","family":"Yaz\u0131c\u0131o\u011flu","sequence":"additional","affiliation":[{"name":"Northeastern University,Department of Mechanical and Industrial Engineering,Boston,MA,02115"}]},{"given":"Derya","family":"Aksaray","sequence":"additional","affiliation":[{"name":"Northeastern University,Department of Electrical and Computer Engineering,Boston,MA,02115"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5132"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16937"},{"key":"ref6","article-title":"Alwayssafe: Reinforcement learning without safety constraint violations during training","author":"Sim\u00e3o","year":"2021","journal-title":"AAMAS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref8","first-page":"1451","article-title":"Safe exploration in markov decision processes","volume-title":"Proceedings of the 29th International Coference on International Conference on Machine Learning","author":"Moldovan","year":"2012"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2876389"},{"key":"ref10","first-page":"483","volume-title":"Cautious Reinforcement Learning with Logical Constraints","author":"Hasanbeig","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-28582-4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref13","article-title":"Safe-critical modular deep reinforcement learning with temporal logic through gaussian processes and control barrier functions","author":"Cai","year":"2021","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636598"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.entcs.2015.10.009"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-63010-4_6"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2017.07.012"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10795-0"},{"issue":"3\u20134","key":"ref19","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"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2015.2452931"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018066"},{"key":"ref22","article-title":"Reinforcement learning under probabilistic spatio-temporal constraints with time windows","author":"Lin","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2023,10,1]]},"location":"Detroit, MI, USA","end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10342259.pdf?arnumber=10342259","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:33:27Z","timestamp":1703032407000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342259\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342259","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}