{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:16:50Z","timestamp":1759331810921,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"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":[[2020,7]]},"DOI":"10.1109\/ijcnn48605.2020.9207384","type":"proceedings-article","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T00:40:33Z","timestamp":1601426433000},"page":"1-8","source":"Crossref","is-referenced-by-count":7,"title":["Safe Reinforcement Learning via Probabilistic Timed Computation Tree Logic"],"prefix":"10.1109","author":[{"given":"Li","family":"Qian","sequence":"first","affiliation":[]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-017-0999-8"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50021-0"},{"article-title":"Safe exploration in markov decision processes","year":"2012","author":"moldovan","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/891"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102352"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-13823-7_31"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-46681-0_51"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12107","article-title":"Safe reinforcement learning via formal methods: Toward safe control through proof and learning","author":"fulton","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1989.70671"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6423(83)90017-5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1023\/B:MACH.0000039779.47329.3a"},{"key":"ref3","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc?a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11797","article-title":"Safe reinforcement learning via shielding","author":"alshiekh","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref5","first-page":"1037","article-title":"Smart exploration in reinforcement learning using absolute temporal difference errors","author":"gehring","year":"2013","journal-title":"Proceedings of the 2013 International Conference on Autonomous Agents and Multi-agent Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793636"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/840"},{"article-title":"Reinforcement learning: An introduction","year":"2018","author":"sutton","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"article-title":"Safe control under uncertainty","year":"2015","author":"sadigh","key":"ref9"},{"key":"ref20","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":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-46029-2_13"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-60692-0_70"},{"article-title":"Openai gym","year":"2016","author":"brockman","key":"ref24"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10295","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"2016","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"}],"event":{"name":"2020 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2020,7,19]]},"location":"Glasgow, United Kingdom","end":{"date-parts":[[2020,7,24]]}},"container-title":["2020 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9200848\/9206590\/09207384.pdf?arnumber=9207384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T17:40:06Z","timestamp":1696786806000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9207384\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/ijcnn48605.2020.9207384","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}