{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:48:51Z","timestamp":1776181731781,"version":"3.50.1"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Guang Dong Basic and Applied Basic Research","award":["2023A1515011813"],"award-info":[{"award-number":["2023A1515011813"]}]},{"name":"NSFC Project","award":["62003328"],"award-info":[{"award-number":["62003328"]}]},{"name":"Shenzhen Basic Key Research","award":["JCYJ20200109115414354"],"award-info":[{"award-number":["JCYJ20200109115414354"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/lra.2024.3427551","type":"journal-article","created":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T17:41:40Z","timestamp":1721324500000},"page":"7477-7484","source":"Crossref","is-referenced-by-count":9,"title":["Attention-Based Distributional Reinforcement Learning for Safe and Efficient Autonomous Driving"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2363-8798","authenticated-orcid":false,"given":"Jia","family":"Liu","sequence":"first","affiliation":[{"name":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7057-9943","authenticated-orcid":false,"given":"Jianwen","family":"Yin","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6498-0234","authenticated-orcid":false,"given":"Zhengmin","family":"Jiang","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3823-6828","authenticated-orcid":false,"given":"Qingyi","family":"Liang","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0157-1393","authenticated-orcid":false,"given":"Huiyun","family":"Li","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3024655"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2024.3352543"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3141\/2623-01"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref6","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dabney","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422557"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref10","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. Conf. Robot Learn.","author":"Dosovitskiy","year":"2017"},{"key":"ref11","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995721"},{"key":"ref13","article-title":"SQIL: Imitation learning via reinforcement learning with sparse rewards","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Reddy","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2022.3174410"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3047129"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3142822"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/robotics12050127"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9921872"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00178"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3141044"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWAMTIP53232.2021.9674096"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04357-7"},{"key":"ref24","first-page":"6193","article-title":"Fully parameterized quantile function for distributional reinforcement learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"32","author":"Yang","year":"2019"},{"key":"ref25","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bellemare","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref27","first-page":"66","article-title":"Learning by cheating","volume-title":"Proc. Conf. Robot Learn.","author":"Chen","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00718"},{"key":"ref29","first-page":"1792","article-title":"Visualizing and understanding ATARI agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Greydanus","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294301"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160449"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10601335\/10604470.pdf?arnumber=10604470","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,20]],"date-time":"2024-07-20T04:47:40Z","timestamp":1721450860000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10604470\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":31,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3427551","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}