{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T22:30:53Z","timestamp":1751409053170,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,24]],"date-time":"2023-09-24T00:00:00Z","timestamp":1695513600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,24]],"date-time":"2023-09-24T00:00:00Z","timestamp":1695513600000},"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":[[2023,9,24]]},"DOI":"10.1109\/itsc57777.2023.10422230","type":"proceedings-article","created":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T18:32:39Z","timestamp":1707849159000},"page":"1643-1650","source":"Crossref","is-referenced-by-count":3,"title":["Modeling Interaction-Aware Driving Behavior using Graph-Based Representations and Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Fabian","family":"Konstantinidis","sequence":"first","affiliation":[{"name":"Pre-Development of Automated Driving, CARIAD SE,Wolfsburg,Germany,38440"}]},{"given":"Moritz","family":"Sackmann","sequence":"additional","affiliation":[{"name":"Pre-Development of Automated Driving, CARIAD SE,Wolfsburg,Germany,38440"}]},{"given":"Ulrich","family":"Hofmann","sequence":"additional","affiliation":[{"name":"Pre-Development of Automated Driving, CARIAD SE,Wolfsburg,Germany,38440"}]},{"given":"Christoph","family":"Stiller","sequence":"additional","affiliation":[{"name":"Institute of Measurement and Control Systems,Karlsruhe In-stitute of Technology (KIT),Karlsruhe,Germany,76131"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2017.2788208"},{"key":"ref2","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"Conference on robot learning","author":"Dosovitskiy","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2010.0084"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995797"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2603007"},{"key":"ref7","article-title":"Feedback in imitation learning: The three regimes of covariate shift","author":"Spencer","year":"2021","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Learning a diverse and cooperative policy for predicting roundabout traffic situations","volume-title":"14. Workshop Fahrerassistenz und automatisiertes Fahren","author":"Sackmann","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2015.7225830"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9565031"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8814080"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564944"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref15","article-title":"Interaction dataset: An international, adversarial and cooperative motion dataset in interactive driving scenarios with semantic maps","author":"Zhan","year":"2019","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294338"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_32"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01154"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812253"},{"key":"ref20","first-page":"895","article-title":"Tnt: Target-driven trajectory prediction","volume-title":"Conference on Robot Learning","author":"Zhao","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01502"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636035"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569929"},{"key":"ref24","first-page":"55","article-title":"Vectorrl: Interpretable graph-based reinforcement learning for automated driving","volume-title":"Proceedings 31. Workshop Computational Intelligence","volume":"25","author":"Diehl","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827165"},{"key":"ref26","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"Lowe","year":"2017","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Prox-imal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref28","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International Conference on Machine Learning","author":"Haarnoja","year":"2018"},{"key":"ref29","article-title":"Is independent learning all you need in the starcraft multi-agent challenge?","author":"De Witt","year":"2020","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref31","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref33","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"What matters in on-policy reinforcement learning? a large-scale empirical study","author":"Andrychowicz","year":"2020","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"}],"event":{"name":"2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)","start":{"date-parts":[[2023,9,24]]},"location":"Bilbao, Spain","end":{"date-parts":[[2023,9,28]]}},"container-title":["2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10420842\/10420843\/10422230.pdf?arnumber=10422230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T06:38:46Z","timestamp":1709447926000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10422230\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,24]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/itsc57777.2023.10422230","relation":{},"subject":[],"published":{"date-parts":[[2023,9,24]]}}}