{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:46:22Z","timestamp":1785858382808,"version":"3.56.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T00:00:00Z","timestamp":1625961600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T00:00:00Z","timestamp":1625961600000},"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":[[2021,7,11]]},"DOI":"10.1109\/iv48863.2021.9575379","type":"proceedings-article","created":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T20:59:16Z","timestamp":1635800356000},"page":"223-230","source":"Crossref","is-referenced-by-count":21,"title":["Meta Reinforcement Learning-Based Lane Change Strategy for Autonomous Vehicles"],"prefix":"10.1109","author":[{"given":"Fei","family":"Ye","sequence":"first","affiliation":[{"name":"California PATH, University of California, Berkeley,Richmond,CA,USA,94804"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pin","family":"Wang","sequence":"additional","affiliation":[{"name":"California PATH, University of California, Berkeley,Richmond,CA,USA,94804"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ching-Yao","family":"Chan","sequence":"additional","affiliation":[{"name":"California PATH, University of California, Berkeley,Richmond,CA,USA,94804"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiucai","family":"Zhang","sequence":"additional","affiliation":[{"name":"GAC R&D Center Silicon Valley Inc.,Sunnyvale,CA,USA,94085"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569448"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917392"},{"key":"ref12","author":"sallab","year":"2017","journal-title":"Meta learning framework for automated driving"},{"key":"ref13","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref14","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref15","author":"saunders","year":"2017","journal-title":"Trial without Error Towards Safe Reinforcement Learning via Human Intervention"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_1"},{"key":"ref17","article-title":"Rl2: Fast reinforcement learning via slow reinforcement learning","author":"duan","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref18","first-page":"5302","article-title":"Meta-reinforcement learning of structured exploration strategies","author":"gupta","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"nagabandi","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref4","author":"zhang","year":"2016","journal-title":"Query-efficient imitation learning for end-to-end autonomous driving"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21918"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref5","article-title":"Chauffeurnet: Learning to drive by imitating the best and synthesizing the worst","author":"bansal","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2019.08.011"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569568"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"ref9","article-title":"Automated lane change strategy using proximal policy optimization-based deep reinforcement learning","author":"ye","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2498841"},{"key":"ref20","article-title":"Learning to reinforcement learn","author":"wang","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref22","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume":"2","author":"kakade","year":"2002","journal-title":"ICML"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"williams","year":"1992","journal-title":"Machine Learning"},{"key":"ref24","author":"alshiekh","year":"2017","journal-title":"Safe reinforcement learning via shielding"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref26","first-page":"63","author":"behrisch","year":"2011","journal-title":"SUMOSimulation of Urban MObility-An Overview"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2019.02.006"}],"event":{"name":"2021 IEEE Intelligent Vehicles Symposium (IV)","location":"Nagoya, Japan","start":{"date-parts":[[2021,7,11]]},"end":{"date-parts":[[2021,7,17]]}},"container-title":["2021 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9575127\/9575130\/09575379.pdf?arnumber=9575379","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:20:44Z","timestamp":1659486044000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9575379\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,11]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/iv48863.2021.9575379","relation":{},"subject":[],"published":{"date-parts":[[2021,7,11]]}}}