{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T04:04:47Z","timestamp":1773547487410,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,9]],"date-time":"2020-10-09T00:00:00Z","timestamp":1602201600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,9]],"date-time":"2020-10-09T00:00:00Z","timestamp":1602201600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,9]],"date-time":"2020-10-09T00:00:00Z","timestamp":1602201600000},"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":[[2020,10,9]]},"DOI":"10.1109\/icca51439.2020.9264552","type":"proceedings-article","created":{"date-parts":[[2020,11,30]],"date-time":"2020-11-30T21:36:44Z","timestamp":1606772204000},"page":"35-40","source":"Crossref","is-referenced-by-count":25,"title":["Zero-Shot Autonomous Vehicle Policy Transfer: From Simulation to Real-World via Adversarial Learning"],"prefix":"10.1109","author":[{"given":"Behdad","family":"Chalaki","sequence":"first","affiliation":[]},{"given":"Logan E.","family":"Beaver","sequence":"additional","affiliation":[]},{"given":"Ben","family":"Remer","sequence":"additional","affiliation":[]},{"given":"Kathy","family":"Jang","sequence":"additional","affiliation":[]},{"given":"Eugene","family":"Vinitsky","sequence":"additional","affiliation":[]},{"given":"Alexandre M.","family":"Bayen","sequence":"additional","affiliation":[]},{"given":"Andreas A.","family":"Malikopoulos","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","first-page":"2817","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref31","article-title":"Openai gym","author":"brockman","year":"2016"},{"key":"ref30","first-page":"128","article-title":"Recent development and applications of SUMO - Simulation of Urban MObility","volume":"5","author":"krajzewicz","year":"2012","journal-title":"International Journal on Advances in Systems and Measurements"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2007.4282788"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1080\/00423114.2020.1730412"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2600504"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2018.04.011"},{"key":"ref12","article-title":"Review of trajectory optimisation for connected automated vehicles","author":"wang","year":"2018","journal-title":"IET Intelligent Transport Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2018.04.011"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref16","article-title":"Alphastar: Mastering the real-time strategy game starcraft ii","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.02.005"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/10\/3\/033001"},{"key":"ref19","first-page":"398","article-title":"Emergent behaviors in mixed-autonomy traffic","author":"wu","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref28","article-title":"Ray rllib: A composable and scalable reinforcement learning library","author":"liang","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2178836"},{"key":"ref27","article-title":"Flow: Architecture and benchmarking for reinforcement learning in traffic control","author":"wu","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.tra.2015.12.001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.03.056"},{"key":"ref29","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2011.6083084"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/0041-1647(69)90109-9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2865561"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2019.2953526"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2018.2873899"},{"key":"ref1","author":"schrank","year":"2015","journal-title":"2015 Urban mobility scorecard"},{"key":"ref20","first-page":"399","article-title":"Benchmarks for reinforcement learning in mixed-autonomy traffic","author":"vinitsky","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref22","article-title":"Expert level control of ramp metering based on multi-task deep reinforcement learning","author":"belletti","year":"2017","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3302509.3313784"},{"key":"ref24","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref25","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2020 IEEE 16th International Conference on Control & Automation (ICCA)","location":"Singapore","start":{"date-parts":[[2020,10,9]]},"end":{"date-parts":[[2020,10,11]]}},"container-title":["2020 IEEE 16th International Conference on Control & Automation (ICCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9264304\/9264308\/09264552.pdf?arnumber=9264552","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:19:10Z","timestamp":1656375550000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9264552\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,9]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icca51439.2020.9264552","relation":{},"subject":[],"published":{"date-parts":[[2020,10,9]]}}}