{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T15:50:55Z","timestamp":1765295455097,"version":"3.28.0"},"reference-count":36,"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\/itsc57777.2023.10422440","type":"proceedings-article","created":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T23:32:39Z","timestamp":1707867159000},"page":"4079-4085","source":"Crossref","is-referenced-by-count":1,"title":["Constrained Multi-Agent Reinforcement Learning Policies for Cooperative Intersection Navigation and Traffic Compliance"],"prefix":"10.1109","author":[{"given":"Fahmy","family":"Adan","sequence":"first","affiliation":[{"name":"Imperial College London,Centre for Transport Studies,Department of Civil and Environmental Engineering,London,U.K.,SW7 2AZ"}]},{"given":"Yuxiang","family":"Feng","sequence":"additional","affiliation":[{"name":"Imperial College London,Centre for Transport Studies,Department of Civil and Environmental Engineering,London,U.K.,SW7 2AZ"}]},{"given":"Panagiotis","family":"Angeloudis","sequence":"additional","affiliation":[{"name":"Imperial College London,Centre for Transport Studies,Department of Civil and Environmental Engineering,London,U.K.,SW7 2AZ"}]},{"given":"Mohammed","family":"Quddus","sequence":"additional","affiliation":[{"name":"Imperial College London,Centre for Transport Studies,Department of Civil and Environmental Engineering,London,U.K.,SW7 2AZ"}]},{"given":"Washington","family":"Ochieng","sequence":"additional","affiliation":[{"name":"Imperial College London,Centre for Transport Studies,Department of Civil and Environmental Engineering,London,U.K.,SW7 2AZ"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Intersection road accident cau-sation: A european view","volume-title":"21st International Technical Conference on the Enhanced Safety of Vehicles","author":"Simon"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3169907"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-008-9062-9"},{"article-title":"Raim: Reinforced autonomous intersection management-aim based on madrl","volume-title":"Proceedings of the NeurIPS","author":"Guillen-Perez","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3407903"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564720"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3054625"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20255"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304606"},{"key":"ref10","article-title":"On a for-mal model of safe and scalable self-driving cars","author":"Shalev-Shwartz","year":"2017","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9921880"},{"key":"ref13","article-title":"Reward (mis)design for autonomous driving","volume-title":"CoRR","volume":"abs\/2104.13906","author":"Knox","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref16","first-page":"816","article-title":"Feudal multi-agent deep reinforcement learning for traffic signal control","volume-title":"Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems (AAMAS)","author":"Ma"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3105426"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102846"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.06.004"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_32"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2019.04.012"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2940641"},{"volume-title":"Harl: A novel hierachical adversary reinforcement learning for automoumous intersection management","year":"2022","author":"Li","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636151"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3207872"},{"key":"ref26","article-title":"Learning to control and coordinate hybrid traffic through robot vehicles at complex and unsignalized intersections","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922164"},{"key":"ref28","article-title":"Safe deep q-network for autonomous vehicles at unsignalized intersection","author":"Mokhtari","year":"2021","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636847"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922166"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5729"},{"key":"ref32","article-title":"Social attention for autonomous decision-making in dense traffic","author":"Leurent","year":"2019","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968560"},{"key":"ref34","article-title":"Smarts: Scalable multi-agent reinforcement learning training school for autonomous driving","author":"Zhou","year":"2020","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS)","author":"Papoudakis","year":"2021"},{"key":"ref36","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","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\/10422440.pdf?arnumber=10422440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T11:48:41Z","timestamp":1709466521000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10422440\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,24]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/itsc57777.2023.10422440","relation":{},"subject":[],"published":{"date-parts":[[2023,9,24]]}}}