{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T15:47:37Z","timestamp":1765295257222,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"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":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9636480","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T20:45:38Z","timestamp":1639687538000},"page":"3506-3511","source":"Crossref","is-referenced-by-count":22,"title":["Motion Planning for Autonomous Vehicles in the Presence of Uncertainty Using Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Kasra","family":"Rezaee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peyman","family":"Yadmellat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Chamorro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAS.2019.8808950"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8916928"},{"key":"ref12","first-page":"1","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"chow","year":"2018","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5870"},{"key":"ref14","first-page":"2892","article-title":"Distributional reinforcement learning with quantile regression","author":"dabney","year":"2018","journal-title":"AAAI Conference on Artificial Intelligence AAAI'10"},{"key":"ref15","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume":"80","author":"dabney","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"journal-title":"Reinforcement Learning An Introduction","year":"1988","author":"sutton","key":"ref16"},{"key":"ref17","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"ICLR 2018 International Conference on Learning Representations 2018"},{"key":"ref18","first-page":"1","article-title":"Distributional soft actor-critic: Off-policy reinforcement learning for addressing value estimation errors","author":"duan","year":"2021","journal-title":"IEEE Transactions on Neural Networks"},{"key":"ref19","first-page":"987","article-title":"Optimal trajectory generation for dynamic street scenarios in a Frenet frame","author":"werling","year":"2010","journal-title":"IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3024655"},{"key":"ref3","first-page":"368","article-title":"Parametric return density estimation for reinforcement learning","author":"morimura","year":"2010","journal-title":"UAI’10 Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"article-title":"End to end learning for self-driving cars","year":"2016","author":"bojarski","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3013234"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793557"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5220\/0007955504220429"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2021,9,27]]},"location":"Prague, Czech Republic","end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09636480.pdf?arnumber=9636480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:54:32Z","timestamp":1652201672000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636480\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636480","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}