{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T06:58:23Z","timestamp":1758265103015},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,5]],"date-time":"2022-06-05T00:00:00Z","timestamp":1654387200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,5]],"date-time":"2022-06-05T00:00:00Z","timestamp":1654387200000},"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":[[2022,6,5]]},"DOI":"10.1109\/iv51971.2022.9827031","type":"proceedings-article","created":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T15:33:28Z","timestamp":1658244808000},"page":"22-28","source":"Crossref","is-referenced-by-count":8,"title":["Learning Reward Models for Cooperative Trajectory Planning with Inverse Reinforcement Learning and Monte Carlo Tree Search"],"prefix":"10.1109","author":[{"given":"Karl","family":"Kurzer","sequence":"first","affiliation":[{"name":"Institute of Applied Informatics and Formal Description Methods, Karlsruhe Institute of Technology,Karlsruhe,Germany,76131"}]},{"given":"Matthias","family":"Bitzer","sequence":"additional","affiliation":[{"name":"Bosch Center for Artificial Intelligence, Robert Bosch GmbH,Renningen,Germany,71272"}]},{"given":"J. Marius","family":"Zollner","sequence":"additional","affiliation":[{"name":"Institute of Applied Informatics and Formal Description Methods, Karlsruhe Institute of Technology,Karlsruhe,Germany,76131"}]}],"member":"263","reference":[{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"article-title":"Maximum entropy deep inverse reinforcement learning","year":"2015","author":"wulfmeier","key":"ref12"},{"key":"ref13","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","author":"finn","year":"2016","journal-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3005126"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref16","article-title":"Monte Carlo theory, methods and examples","author":"owen","year":"2013","journal-title":"Owen Art B"},{"key":"ref4","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"Proc Seventh Int Conf Machine Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196795"},{"key":"ref6","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"2008","journal-title":"Proceedings of the 23rd National Conference on Artificial Intelligence"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759328"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139555"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IV48863.2021.9575669"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500427"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569988"}],"event":{"name":"2022 IEEE Intelligent Vehicles Symposium (IV)","start":{"date-parts":[[2022,6,4]]},"location":"Aachen, Germany","end":{"date-parts":[[2022,6,9]]}},"container-title":["2022 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9826996\/9826997\/09827031.pdf?arnumber=9827031","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,8]],"date-time":"2022-08-08T16:04:26Z","timestamp":1659974666000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9827031\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,5]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/iv51971.2022.9827031","relation":{},"subject":[],"published":{"date-parts":[[2022,6,5]]}}}