{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:58:32Z","timestamp":1759334312223,"version":"build-2065373602"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T00:00:00Z","timestamp":1752624000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T00:00:00Z","timestamp":1752624000000},"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":["62077029,62277030"],"award-info":[{"award-number":["62077029,62277030"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003405","name":"Nanjing University of Aeronautics and Astronautics","doi-asserted-by":"publisher","award":["NJ2020022"],"award-info":[{"award-number":["NJ2020022"]}],"id":[{"id":"10.13039\/501100003405","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,16]]},"DOI":"10.1109\/qrs65678.2025.00068","type":"proceedings-article","created":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T17:51:28Z","timestamp":1759168288000},"page":"634-643","source":"Crossref","is-referenced-by-count":0,"title":["A Reinforcement Learning Algorithm for Safety Decision Making in Autonomous Driving Systems with Reward Machine Guidance"],"prefix":"10.1109","author":[{"given":"Junge","family":"Huang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Jiangsu Normal University,Xuzhou,Jiangsu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Jiangsu Normal University,Xuzhou,Jiangsu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinyong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Xuzhou University of Technology,Xuzhou,Jiangsu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Jiangsu Normal University,Xuzhou,Jiangsu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miaoer","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Jiangsu Normal University,Xuzhou,Jiangsu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2983149"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-024-06543-w"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23940\/ijpe.25.06.p6.339350"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106685"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/360248.360251"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30080-9_7"},{"key":"ref8","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":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12440"},{"key":"ref10","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"Conference on robot learning","author":"Dosovitskiy","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20594"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v32i1.19844"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3227122"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-60915-6_6"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-18088-5_22"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10703-017-0286-7"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10703-016-0241-z"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23820-3_7"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS.2017.00035"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS61052.2024.00032"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.3.372"},{"key":"ref22","first-page":"3976","article-title":"Counterfactual data augmentation using locally factored dynamics","volume":"33","author":"Pitis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0304-3975(94)90010-8"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207384"},{"key":"ref26","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"International conference on machine learning","author":"Silver","year":"2014"},{"key":"ref27","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"}],"event":{"name":"2025 25th International Conference on Software Quality, Reliability and Security (QRS)","start":{"date-parts":[[2025,7,16]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,7,20]]}},"container-title":["2025 25th International Conference on Software Quality, Reliability and Security (QRS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11173421\/11173424\/11173512.pdf?arnumber=11173512","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T14:29:09Z","timestamp":1759242549000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11173512\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,16]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/qrs65678.2025.00068","relation":{},"subject":[],"published":{"date-parts":[[2025,7,16]]}}}