{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T16:01:31Z","timestamp":1782835291133,"version":"3.54.5"},"reference-count":36,"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\/itsc48978.2021.9564972","type":"proceedings-article","created":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T19:52:26Z","timestamp":1635191546000},"page":"1745-1752","source":"Crossref","is-referenced-by-count":14,"title":["Quick Learner Automated Vehicle Adapting its Roadmanship to Varying Traffic Cultures with Meta Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Songan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huei","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"H. Eric","family":"Tseng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"crossref","first-page":"24972","DOI":"10.1073\/pnas.1820676116","article-title":"Social behavior for autonomous vehicles","volume":"116","author":"schwarting","year":"0","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"ref32","author":"leurent","year":"2018","journal-title":"An Environment for Autonomous Driving Decision-Making"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00173"},{"key":"ref30","author":"stewart","year":"2018","journal-title":"Why people keep rear-ending self-driving cars"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2019.00147"},{"key":"ref35","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"ref10","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"ng","year":"2000","journal-title":"ICML"},{"key":"ref11","author":"eysenbach","year":"2018","journal-title":"Diversity is all you need Learning skills without a reward function"},{"key":"ref12","first-page":"1","article-title":"Safe reinforcement learning for autonomous vehicles through parallel constrained policy optimization","author":"wen","year":"0","journal-title":"2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2019.8914621"},{"key":"ref14","author":"nageshrao","year":"2020","journal-title":"Vehicle adaptive learning"},{"key":"ref15","author":"chow","year":"2018","journal-title":"A lyapunov-based approach to safe reinforcement learning"},{"key":"ref16","article-title":"Safe exploration and optimization of constrained mdps using gaussian processes","volume":"32","author":"wachi","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref17","author":"dulac-arnold","year":"2019","journal-title":"Challenges of realworld reinforcement learning"},{"key":"ref18","first-page":"52","article-title":"Robust reinforcement learning for autonomous driving","author":"jaafra","year":"2019","journal-title":"APIa"},{"key":"ref19","author":"nagabandi","year":"2018","journal-title":"Learning to Adapt in Dynamic Real-World Environments Through Meta-Reinforcement Learning"},{"key":"ref28","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","author":"rakelly","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref4","first-page":"924","article-title":"Con-current reinforcement learning from customer interactions","author":"silver","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref27","author":"gupta","year":"2018","journal-title":"Meta-reinforcement learning of structured exploration strategies"},{"key":"ref3","author":"melis","year":"2017","journal-title":"On the state of the art of evaluation in neural language models"},{"key":"ref6","first-page":"1","volume":"7","author":"bazzan","year":"2013","journal-title":"Introduction to Intelligent Systems in Traffic and Transportation"},{"key":"ref29","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":"International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbx044"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref7","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref9","author":"li","year":"2017","journal-title":"Deep reinforcement learning An overview"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2019.2896986"},{"key":"ref20","first-page":"357","article-title":"One-shot visual imitation learning via meta-learning","author":"finn","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref22","author":"duan","year":"2016","journal-title":"RL2 Fast reinforcement learning via slow reinforcement learning"},{"key":"ref21","author":"yu","year":"2018","journal-title":"One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning"},{"key":"ref24","author":"heess","year":"2015","journal-title":"Memory-based control with recurrent neural networks"},{"key":"ref23","author":"wang","year":"2016","journal-title":"Learning to reinforcement learn"},{"key":"ref26","author":"rothfuss","year":"2018","journal-title":"Promp Proximal meta-policy search"},{"key":"ref25","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"0","journal-title":"International Conference on Machine Learning"}],"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\/09564972.pdf?arnumber=9564972","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:47:38Z","timestamp":1652197658000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9564972\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,19]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/itsc48978.2021.9564972","relation":{},"subject":[],"published":{"date-parts":[[2021,9,19]]}}}