{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:35:04Z","timestamp":1730255704563,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9196778","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T17:25:46Z","timestamp":1600190746000},"page":"6419-6425","source":"Crossref","is-referenced-by-count":5,"title":["Driving Style Encoder: Situational Reward Adaptation for General-Purpose Planning in Automated Driving"],"prefix":"10.1109","author":[{"given":"Sascha","family":"Rosbach","sequence":"first","affiliation":[]},{"given":"Vinit","family":"James","sequence":"additional","affiliation":[]},{"given":"Simon","family":"Grosjohann","sequence":"additional","affiliation":[]},{"given":"Silviu","family":"Homoceanu","sequence":"additional","affiliation":[]},{"given":"Xing","family":"Li","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Roth","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2002.1023403"},{"key":"ref11","first-page":"897","article-title":"Apprenticeship learning about multiple intentions","author":"babes","year":"2011","journal-title":"Proc Int Conf Machine Learning (ICML)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2015.7225745"},{"key":"ref13","first-page":"305","article-title":"Nonparametric Bayesian inverse reinforcement learning for multiple reward functions","author":"choi","year":"2012","journal-title":"Adv in Neural Info Proc Syst"},{"key":"ref14","first-page":"49","article-title":"Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization","author":"finn","year":"2016","journal-title":"J of Machine Learning Research"},{"key":"ref15","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Adv in Neural Info Proc Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICoIAS.2019.00025"},{"article-title":"A survey of inverse reinforcement learning: Challenges, methods and progress","year":"2018","author":"arora","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094679"},{"key":"ref19","first-page":"3137","article-title":"A generalized path integral control approach to reinforcement learning","volume":"11","author":"theodorou","year":"2010","journal-title":"J of Machine Learning Research"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353876"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139555"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-658-21954-3"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968205"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917722396"},{"key":"ref7","first-page":"1507.04888","article-title":"Maximum Entropy Deep Inverse Reinforcement Learning","author":"wulfmeier","year":"2015"},{"key":"ref2","first-page":"663","article-title":"Algorithms for Inverse Reinforcement Learning","author":"ng","year":"2000","journal-title":"Proc Int Conf Machine Learning (ICML)"},{"article-title":"Reinforcement learning and control as probabilistic inference: Tutorial and review","year":"2018","author":"levine","key":"ref1"},{"key":"ref9","article-title":"Parallel Algorithms for Real-time Motion Planning","author":"mcnaughton","year":"2011","journal-title":"Ph D Dissertation"},{"key":"ref20","first-page":"1433","article-title":"Maximum Entropy Inverse Reinforcement Learning","volume":"8","author":"ziebart","year":"2008","journal-title":"Proc Nat Conf Art Intel (AAAI)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2011.6082803"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2020,5,31]]},"location":"Paris, France","end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09196778.pdf?arnumber=9196778","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:21:31Z","timestamp":1656361291000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9196778\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9196778","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}