{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T09:58:43Z","timestamp":1776333523505,"version":"3.51.2"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801946","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"1002-1009","source":"Crossref","is-referenced-by-count":3,"title":["Agent-Agnostic Centralized Training for Decentralized Multi-Agent Cooperative Driving"],"prefix":"10.1109","author":[{"given":"Shengchao","family":"Yan","sequence":"first","affiliation":[{"name":"University of Freiburg,Department of Computer Science,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lukas","family":"K\u00f6nig","sequence":"additional","affiliation":[{"name":"Institute for Neural Computation, Ruhr University Bochum,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wolfram","family":"Burgard","sequence":"additional","affiliation":[{"name":"University of Technology Nuremberg,Department of Engineering,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Leveraging the capabilities of connected and autonomous vehicles and multi-agent reinforcement learning to mitigate highway bottleneck congestion","author":"Ha","year":"2020","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/25.806796"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340784"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2551540"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3121807"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3087314"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3582576"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IV48863.2021.9575676"},{"key":"ref9","first-page":"946","article-title":"Socially-attentive policy optimization in multi-agent self-driving system","volume-title":"Proc. of Conference on Robot Learning (CoRL)","author":"Dai"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2014.6958095"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.2971427"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.008"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref15","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. of the Conference on Neural Information Processing Systems (NeurIPS)","volume":"30","author":"Lowe"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2016.7795595"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2004.1336386"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-03991-1","volume-title":"The DARPA urban challenge: autonomous vehicles in city traffic.","volume":"56","author":"Buehler","year":"2009"},{"key":"ref19","first-page":"10 784","article-title":"Learning to simulate self-driven particles system with coordinated policy optimization","volume-title":"Proc. of the Conference on Neural Information Processing Systems (NeurIPS)","author":"Peng"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968560"},{"key":"ref21","first-page":"3962","article-title":"Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world","volume-title":"Proc. of the Conference on Neural Information Processing Systems (NeurIPS)","volume":"35","author":"Vinitsky"},{"key":"ref22","first-page":"398","article-title":"Emergent behaviors in mixed-autonomy traffic","volume-title":"Proc. of Conference on Robot Learning (CoRL)","volume":"78","author":"Wu"},{"key":"ref23","first-page":"399","article-title":"Benchmarks for reinforcement learning in mixed-autonomy traffic","volume-title":"Proc. of Conference on Robot Learning (CoRL)","volume":"87","author":"Vinitsky"},{"key":"ref24","article-title":"Waymo\u2019s driverless ride-hailing service hits the one-year mark","year":"2021"},{"key":"ref25","first-page":"417","article-title":"Do you want your autonomous car to drive like you?","volume-title":"Proc. of ACM\/IEEE International Conference on Human-Robot Interaction (HRI)","author":"Basu"},{"key":"ref26","article-title":"Safe and Efficient Reinforcement Learning for Behavioural Planning in Autonomous Driving","volume-title":"Theses, Universit\u00e9 de Lille","author":"Leurent","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"key":"ref28","first-page":"105","article-title":"Sumo\u2019s lane-changing model","volume-title":"LECTURE NOTES IN CONTROL AND INFORMATION SCIENCES","volume":"13","author":"Erdmann","year":"2015"},{"key":"ref29","first-page":"1","article-title":"Extending the intelligent driver model in sumo and verifying the drive off trajectories with aerial measurements","volume-title":"SUMO Conference Proceedings","volume":"1","author":"Salles"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610949"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569448"},{"key":"ref32","article-title":"Social attention for autonomous decision-making in dense traffic","author":"Leurent","year":"2019","journal-title":"CoRR"},{"key":"ref33","first-page":"10 524","article-title":"On layer normalization in the transformer architecture","volume-title":"Proc. of the International Conference on Machine Learning (ICML)","volume":"119","author":"Xiong"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref35","first-page":"3053","article-title":"RLlib: Abstractions for distributed reinforcement learning","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Liang"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10801946.pdf?arnumber=10801946","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T06:59:08Z","timestamp":1735196348000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801946\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801946","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}