{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T01:00:44Z","timestamp":1755219644439,"version":"3.43.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"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":[[2025,6,22]]},"DOI":"10.1109\/iv64158.2025.11097389","type":"proceedings-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T17:54:55Z","timestamp":1754502895000},"page":"2067-2073","source":"Crossref","is-referenced-by-count":0,"title":["Decentralized Reinforcement Learning for Multi-Agent Navigation in Unconstrained Environments"],"prefix":"10.1109","author":[{"given":"Felix","family":"Forster","sequence":"first","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Computer Vision Group,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qadeer","family":"Khan","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Computer Vision Group,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Cremers","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich,Computer Vision Group,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"End to end learning for self-driving cars","year":"2016","author":"Bojarski","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594090"},{"key":"ref3","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume":"1","author":"Pomerleau","year":"1989","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/itsc57777.2023.10422072"},{"key":"ref5","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"preprint"},{"key":"ref6","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"preprint"},{"key":"ref7","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the 35th ICML, ser. Proceedings of Machine Learning Research","volume":"80","author":"Haarnoja","year":"2018"},{"key":"ref8","article-title":"Scalable multi-agent reinforcement learning through intelligent information aggregation","author":"Nayak","year":"2023","journal-title":"ICML"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112124"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3329530"},{"key":"ref11","article-title":"Graph neural network and reinforcement learning for multi-agent cooperative control of connected autonomous vehicles","author":"C.","year":"2021","journal-title":"Computer-Aided Civil and Infrastructure Engineering"},{"key":"ref12","article-title":"Learning transferable cooperative behavior in multi-agent teams","author":"A.","year":"2019","journal-title":"arXiv preprint"},{"volume-title":"Graph convolutional reinforcement learning","year":"2018","author":"Jiang","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2001.933130"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.031"},{"volume-title":"Learning by cheating","year":"2019","author":"Chen","key":"ref16"},{"key":"ref17","article-title":"Learning to navigate in cities without a map","author":"Mirowski","year":"2018","journal-title":"NeurIPS"},{"key":"ref18","article-title":"The streetlearn environment and dataset","volume":"abs\/1903.01292","author":"Mirowski","year":"2019","journal-title":"ArXiv"},{"key":"ref19","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proceedings of the 1st Annual Conference on Robot Learning","author":"Dosovitskiy","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200245"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01671"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-04478-8"},{"volume-title":"Gymnasium: A standard interface for reinforcement learning environments","year":"2024","author":"Towers","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IV55152.2023.10186793"},{"key":"ref25","article-title":"Graph and recurrent neural network-based vehicle trajectory prediction for highway driving","author":"M","year":"2023","journal-title":"2021 IEEE ITSC"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127220"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827155"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2019.2903261"},{"key":"ref29","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2025.3530348"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.001"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.056"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.11.054"}],"event":{"name":"2025 IEEE Intelligent Vehicles Symposium (IV)","start":{"date-parts":[[2025,6,22]]},"location":"Cluj-Napoca, Romania","end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11097351\/11097337\/11097389.pdf?arnumber=11097389","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T04:58:28Z","timestamp":1754542708000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11097389\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/iv64158.2025.11097389","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}