{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T17:52:57Z","timestamp":1790877177982,"version":"4.1.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:00:00Z","timestamp":1665187200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:00:00Z","timestamp":1665187200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2018AAA0102804"],"award-info":[{"award-number":["2018AAA0102804"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,8]]},"DOI":"10.1109\/itsc55140.2022.9921741","type":"proceedings-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:40:13Z","timestamp":1667526013000},"page":"1063-1069","source":"Crossref","is-referenced-by-count":22,"title":["Autonomous Highway Merging in Mixed Traffic Using Reinforcement Learning and Motion Predictive Safety Controller"],"prefix":"10.1109","author":[{"given":"Qianqian","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Engineering and Science, Shanghai University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengying","family":"Dang","sequence":"additional","affiliation":[{"name":"Michigan State University,Department of Mechanical Engineering,East Lansing,MI,USA,48824"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechatronic Engineering and Automation, Shanghai University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqiang","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Mechatronic Engineering and Automation, Shanghai University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995935"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8916924"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593420"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197132"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304841"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564954"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2916354"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619572"},{"key":"ref17","author":"christodoulou","year":"2019","journal-title":"Soft actor-critic for discrete action settings"},{"key":"ref16","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1115\/DSCC2017-5099"},{"key":"ref18","author":"chen","year":"2021","journal-title":"Deep Multi-agent Reinforcement Learning for Highway On-Ramp Merging in Mixed Traffic"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9608"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"},{"key":"ref26","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref25","article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","volume":"30","author":"wu","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147626"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2001.948767"},{"key":"ref27","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref8","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197559"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2926677"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.02.003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/01441647.2014.983210"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460766"}],"event":{"name":"2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)","location":"Macau, China","start":{"date-parts":[[2022,10,8]]},"end":{"date-parts":[[2022,10,12]]}},"container-title":["2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9921415\/9921739\/09921741.pdf?arnumber=9921741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T22:59:10Z","timestamp":1677538750000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9921741\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,8]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/itsc55140.2022.9921741","relation":{},"subject":[],"published":{"date-parts":[[2022,10,8]]}}}