{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:54:42Z","timestamp":1775066082506,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"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":[[2019,6]]},"DOI":"10.1109\/ivs.2019.8813803","type":"proceedings-article","created":{"date-parts":[[2019,8,29]],"date-time":"2019-08-29T21:11:26Z","timestamp":1567113086000},"page":"1469-1476","source":"Crossref","is-referenced-by-count":67,"title":["Safe Reinforcement Learning with Scene Decomposition for Navigating Complex Urban Environments"],"prefix":"10.1109","author":[{"given":"Maxime","family":"Bouton","sequence":"first","affiliation":[]},{"given":"Alireza","family":"Nakhaei","sequence":"additional","affiliation":[]},{"given":"Kikuo","family":"Fujimura","sequence":"additional","affiliation":[]},{"given":"Mykel J.","family":"Kochenderfer","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Tactical decision making for lane changing with deep reinforcement learning","author":"mukadam","year":"2017","journal-title":"NIPS Workshop on Machine Learning for Intelligent Transportation Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569448"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11797","article-title":"Safe reinforcement learning via shielding","author":"alshiekh","year":"2018","journal-title":"AAAI Conference on Artificial Intelligence (AAAI)"},{"key":"ref13","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/10187.001.0001"},{"key":"ref15","first-page":"529","volume":"518","author":"mnih","year":"2015","journal-title":"Human-level control through deep reinforcement learning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50052-9"},{"key":"ref17","article-title":"Reinforcement learning with probabilistic guarantees for autonomous driving","author":"bouton","year":"2018","journal-title":"UAI Workshop on Safety Risk and Uncertainty in Reinforcement Learning"},{"key":"ref18","author":"baier","year":"2008","journal-title":"Principles of Model Checking"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353874"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2017.2788208"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995818"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500556"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317839"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569316"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2014.6957722"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2011.06.002"},{"key":"ref9","article-title":"A comprehensive survey on safe reinforcement learning","author":"garc\u00eda","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref20","article-title":"Learning with ensembles: How overfitting can be useful","author":"sollich","year":"1995","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2514\/1.54805"},{"key":"ref21","article-title":"Deep variational reinforcement learning for pomdps","author":"igl","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref24","article-title":"Utility decomposition with deep corrections for scalable planning under uncertainty","author":"bouton","year":"2018","journal-title":"International Conference on Autonomous Agents and Multiagent Systems (AAMAS)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/664"}],"event":{"name":"2019 IEEE Intelligent Vehicles Symposium (IV)","location":"Paris, France","start":{"date-parts":[[2019,6,9]]},"end":{"date-parts":[[2019,6,12]]}},"container-title":["2019 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8792328\/8813768\/08813803.pdf?arnumber=8813803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T13:10:31Z","timestamp":1695129031000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8813803\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/ivs.2019.8813803","relation":{},"subject":[],"published":{"date-parts":[[2019,6]]}}}