{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:32:51Z","timestamp":1772908371201,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9560777","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"1028-1035","source":"Crossref","is-referenced-by-count":10,"title":["Amortized Q-learning with Model-based Action Proposals for Autonomous Driving on Highways"],"prefix":"10.1109","author":[{"given":"Branka","family":"Mirchevska","sequence":"first","affiliation":[]},{"given":"Maria","family":"Hugle","sequence":"additional","affiliation":[]},{"given":"Gabriel","family":"Kalweit","sequence":"additional","affiliation":[]},{"given":"Moritz","family":"Werling","sequence":"additional","affiliation":[]},{"given":"Joschka","family":"Boedecker","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917192"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20248"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1504\/IJVAS.2005.008237"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2007.894653"},{"key":"ref5","author":"van Hasselt","year":"2015","journal-title":"Deep Reinforcement Learning with Double Q-learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569568"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968560"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197086"},{"key":"ref9","article-title":"Interpretable Multi Time-scale Constraints in Model-free Deep Reinforcement Learning for Autonomous Driving","author":"Kalweit","year":"2020"},{"key":"ref10","author":"Kalweit","year":"2020","journal-title":"Deep Inverse Q-learning with Constraints"},{"key":"ref11","article-title":"Recent Development and Applications of SUMO - Simulation of Urban MObility","volume":"3&4","author":"Krajzewicz","year":"2012","journal-title":"International Journal On Advances in Systems and Measurements"},{"key":"ref12","article-title":"Efficient Hyperparameter Optimization and Infinitely Many Armed Bandits","author":"Li","year":"2016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569448"},{"key":"ref14","author":"Mnih","year":"2013","journal-title":"Playing Atari with Deep Reinforcement Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03991-1_3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-105157"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989224"},{"key":"ref18","author":"Shalev-Shwartz","year":"2016","journal-title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref22","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20255"},{"key":"ref25","author":"Wang","year":"2018","journal-title":"A Reinforcement Learning Based Approach for Automated Lane Change Maneuvers"},{"key":"ref26","author":"Wang","year":"2019","journal-title":"Quadratic Q-network for Learning Continuous Control for Autonomous Vehicles"},{"key":"ref27","author":"Wang","year":"2019","journal-title":"Deep Reinforcement Learning for Autonomous Driving"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509799"},{"key":"ref30","article-title":"Q-Learning in enormous action spaces via amortized approximate maximization","author":"Van de Wiele","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.01.003"},{"key":"ref32","first-page":"3391","article-title":"Deep Sets","volume-title":"Advances in Neural Information Processing Systems 30","author":"Zaheer","year":"2017"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","location":"Xi'an, China","start":{"date-parts":[[2021,5,30]]},"end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09560777.pdf?arnumber=9560777","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T01:03:08Z","timestamp":1706058188000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9560777\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9560777","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}