{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T16:46:31Z","timestamp":1774716391012,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"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":[[2021,9,19]]},"DOI":"10.1109\/itsc48978.2021.9564880","type":"proceedings-article","created":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T19:52:26Z","timestamp":1635191546000},"page":"3462-3469","source":"Crossref","is-referenced-by-count":9,"title":["Learn collision-free self-driving skills at urban intersections with model-based reinforcement learning"],"prefix":"10.1109","author":[{"given":"Yang","family":"Guan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangang","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haitong","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengbo Eben","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16595-0_16"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0954407020906627"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3024655"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref14","author":"li","year":"2020","journal-title":"Reinforcement learning and control"},{"key":"ref15","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref16","first-page":"1","article-title":"Carla: An open urban driving simulator","author":"dosovitskiy","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3026111"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s42154-020-00113-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2013.02.001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2942089"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139514"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"ref2","article-title":"Hierarchical reinforcement learning for self-driving decision-making without reliance on labeled driving data","author":"duan","year":"2019","journal-title":"IET Intelligent Transport Systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2015.07.013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6631297"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref22","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-018-0139-4"}],"event":{"name":"2021 IEEE International Intelligent Transportation Systems Conference (ITSC)","location":"Indianapolis, IN, USA","start":{"date-parts":[[2021,9,19]]},"end":{"date-parts":[[2021,9,22]]}},"container-title":["2021 IEEE International Intelligent Transportation Systems Conference (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9564393\/9564395\/09564880.pdf?arnumber=9564880","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:47:42Z","timestamp":1652197662000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9564880\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,19]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/itsc48978.2021.9564880","relation":{},"subject":[],"published":{"date-parts":[[2021,9,19]]}}}