{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T09:56:16Z","timestamp":1766138176395,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"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":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981759","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"5077-5082","source":"Crossref","is-referenced-by-count":6,"title":["Accelerated Reinforcement Learning for Temporal Logic Control Objectives"],"prefix":"10.1109","author":[{"given":"Yiannis","family":"Kantaros","sequence":"first","affiliation":[{"name":"Washington University in St. Louis,Department of Electrical and Systems Engineering,St. Louis,MO,USA,63130"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17462-0_27"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3302509.3311053"},{"key":"ref3","article-title":"Reinforcement learning with probabilistic guarantees for autonomous driving","author":"Bouton","year":"2019","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9028919"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196796"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561903"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS48487.2020.00017"},{"key":"ref8","article-title":"Continuous motion planning with temporal logic specifications using deep neural networks","author":"Wang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Compositional reinforcement learning from logical specifications","volume-title":"Thirty-Fifth Conference on Neural Information Processing Systems","author":"Jothimurugan","year":"2021"},{"key":"ref10","first-page":"2107","article-title":"Using reward machines for high-level task specification and decomposition in reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Icarte","year":"2018"},{"key":"ref11","first-page":"6708","article-title":"On efficiency in hierarchical reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Wen","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12440"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13326"},{"key":"ref14","article-title":"Overcoming exploration: Deep reinforcement learning in complex environments from temporal logic specifications","author":"Cai","year":"2022","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref17","article-title":"Boltzmann exploration done right","volume-title":"arXiv preprint","author":"Cesa-Bianchi","year":"2017"},{"issue":"2","key":"ref18","first-page":"235","article-title":"Finite-time analysis of the multiarmed bandit problem","volume-title":"Machine learning","volume":"47","author":"Auer","year":"2002"},{"key":"ref19","article-title":"Ucb exploration via q-ensembles","author":"Chen","year":"2017","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"A survey of exploration methods in reinforcement learning","author":"Amin","year":"2021","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2005.1570410"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9519-z"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989036"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2626400"},{"volume-title":"Principles of model checking","year":"2008","author":"Baier","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920913922"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3144073"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623517"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316887"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SCIS-ISIS.2014.7044672"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2022,10,23]]},"location":"Kyoto, Japan","end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981759.pdf?arnumber=9981759","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T06:01:04Z","timestamp":1706767264000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981759\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981759","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}