{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T17:48:46Z","timestamp":1769881726249,"version":"3.49.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9811618","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"1578-1584","source":"Crossref","is-referenced-by-count":3,"title":["Deep Surrogate Q-Learning for Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Maria","family":"Kalweit","sequence":"first","affiliation":[{"name":"University of Freiburg,Neurorobotics Lab,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gabriel","family":"Kalweit","sequence":"additional","affiliation":[{"name":"University of Freiburg,Neurorobotics Lab,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moritz","family":"Werling","sequence":"additional","affiliation":[{"name":"BMWGroup,Unterschleissheim,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joschka","family":"Boedecker","sequence":"additional","affiliation":[{"name":"University of Freiburg,Neurorobotics Lab,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569552"},{"key":"ref11","first-page":"3391","article-title":"Deep sets","volume":"30","author":"zaheer","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500427"},{"key":"ref13","article-title":"Towards practical hierarchical reinforcement learning for multi-lane autonomous driving","author":"nosrati","year":"2018","journal-title":"2018 NIPS MLITS Workshop"},{"key":"ref14","first-page":"1885","author":"kaushik","year":"2018","journal-title":"Overtaking maneuvers in simulated highway driving using deep reinforcement learning"},{"key":"ref15","article-title":"Tactical decision making for lane changing with deep reinforcement learning","author":"mukadam","year":"2017","journal-title":"NIPS Workshop on Machine Learning for Intelligent Transportation Systems"},{"key":"ref16","article-title":"DeepTraffic: Driving Fast through Dense Traffic with Deep Reinforcement Learning","author":"fridman","year":"2018","journal-title":"ArXiv e-prints"},{"key":"ref17","article-title":"Prioritized Experience Replay","author":"schaul","year":"2015","journal-title":"ArXiv e-prints"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref19","article-title":"Adam: A method for stochastic optimization","volume":"abs 1412 6980","author":"kingma","year":"2014","journal-title":"CoRR"},{"key":"ref4","first-page":"32","article-title":"Reinforcement learning for autonomous maneuvering in highway scenarios","author":"mirchevska","year":"2017","journal-title":"Workshop for Driving Assistance Systems and Autonomous Driving"},{"key":"ref3","first-page":"39:1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968560"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569448"},{"key":"ref8","article-title":"Deep inverse q-learning with constraints","volume":"33","author":"kalweit","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197086"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref1","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":"ref9","article-title":"Deep constrained q-learning","volume":"abs 2003 9398","author":"kalweit","year":"2020","journal-title":"CoRR"},{"key":"ref20","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning ICML 2018"},{"key":"ref21","first-page":"12","article-title":"Recent development and applications of sumo - simulation of urban mobility","volume":"3","author":"krajzewicz","year":"2012","journal-title":"International Journal on Advances in Systems and Measurements"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09811618.pdf?arnumber=9811618","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:08:53Z","timestamp":1667516933000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9811618\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9811618","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}