{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T22:43:36Z","timestamp":1773269016326,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:00:00Z","timestamp":1665187200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:00:00Z","timestamp":1665187200000},"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":[[2022,10,8]]},"DOI":"10.1109\/itsc55140.2022.9922345","type":"proceedings-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:40:13Z","timestamp":1667526013000},"page":"1913-1920","source":"Crossref","is-referenced-by-count":2,"title":["How to Learn from Risk: Explicit Risk-Utility Reinforcement Learning for Efficient and Safe Driving Strategies"],"prefix":"10.1109","author":[{"given":"Lukas M.","family":"Schmidt","sequence":"first","affiliation":[{"name":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS,Nuremberg,Germany"}]},{"given":"Sebastian","family":"Rietsch","sequence":"additional","affiliation":[{"name":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS,Nuremberg,Germany"}]},{"given":"Axel","family":"Plinge","sequence":"additional","affiliation":[{"name":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS,Nuremberg,Germany"}]},{"given":"Bjoern M.","family":"Eskofier","sequence":"additional","affiliation":[{"name":"Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Erlangen,Germany"}]},{"given":"Christopher","family":"Mutschler","sequence":"additional","affiliation":[{"name":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS,Nuremberg,Germany"}]}],"member":"263","reference":[{"key":"ref13","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction Adaptive Computations and Machine Learning"},{"key":"ref12","article-title":"Reward constrained policy optimization","author":"tessler","year":"0","journal-title":"Int Conf Learning Representations"},{"key":"ref15","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":"ref14","author":"altman","year":"1999","journal-title":"Constrained Markov Decision Processes Stochastic Modeling"},{"key":"ref31","author":"rietsch","year":"2022","journal-title":"Driver dojo A benchmark for generalizable reinforcement learning for autonomous driving"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref11","author":"dalal","year":"2018","journal-title":"Safe exploration in continuous action spaces"},{"key":"ref33","first-page":"3319","article-title":"Axiomatic attribution for deep networks","author":"sundararajan","year":"0","journal-title":"Int Conf on Machine Learning"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref32","author":"dosovitskiy","year":"2017","journal-title":"CARLA An Open Urban Driving Simulator"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12228"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922205"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294407"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569568"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569448"},{"key":"ref18","author":"ye","year":"2020","journal-title":"Automated lane change strategy using proximal policy optimization-based deep reinforcement learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1666"},{"key":"ref23","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3233231"},{"key":"ref25","author":"kalweit","year":"2020","journal-title":"Deep constrained Q-learning"},{"key":"ref20","author":"leurent","year":"2020","journal-title":"Safe and efficient reinforcement learning for behavioural planning in autonomous driving"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2019.2955905"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294396"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref27","author":"hill","year":"2018","journal-title":"Stable Baselines"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref8","first-page":"9133","article-title":"Responsive safety in reinforcement learning by PID lagrangian methods","author":"stooke","year":"0","journal-title":"Intl Conf Machine Learning"},{"key":"ref7","article-title":"Reward constrained policy optimization","author":"tessler","year":"0","journal-title":"Int Conf Learning Representations"},{"key":"ref9","article-title":"Maneuver planning and learning: A lane selection approach for highly automated vehicles in highway scenarios","author":"men\u00e9ndez-romero","year":"0","journal-title":"IEEE Conf Intell Transp Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IV48863.2021.9575328"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v38i3.2741"},{"key":"ref6","article-title":"Conservative safety critics for exploration","author":"bharadhwaj","year":"2021","journal-title":"Int Conf Learning Representations"},{"key":"ref5","first-page":"22","article-title":"Constrained policy optimization","volume":"70","author":"achiam","year":"0","journal-title":"Int Conf on Machine Learning ser Proc Machine Learning Research"}],"event":{"name":"2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)","location":"Macau, China","start":{"date-parts":[[2022,10,8]]},"end":{"date-parts":[[2022,10,12]]}},"container-title":["2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9921415\/9921739\/09922345.pdf?arnumber=9922345","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T23:05:50Z","timestamp":1677539150000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9922345\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,8]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/itsc55140.2022.9922345","relation":{},"subject":[],"published":{"date-parts":[[2022,10,8]]}}}