{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T09:52:40Z","timestamp":1762509160970,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,2]],"date-time":"2024-06-02T00:00:00Z","timestamp":1717286400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,2]],"date-time":"2024-06-02T00:00:00Z","timestamp":1717286400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003024","name":"Shanghai Education Development Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003024","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,2]]},"DOI":"10.1109\/iv55156.2024.10588863","type":"proceedings-article","created":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T17:19:28Z","timestamp":1721063968000},"page":"2255-2260","source":"Crossref","is-referenced-by-count":1,"title":["Autonomous Intersection Management with Heterogeneous Vehicles: A Multi-Agent Reinforcement Learning Approach"],"prefix":"10.1109","author":[{"given":"Kaixin","family":"Chen","sequence":"first","affiliation":[{"name":"Tongji University,School of Software Engineering,Shanghai,China,200092"}]},{"given":"Bing","family":"Li","sequence":"additional","affiliation":[{"name":"Tongji University,School of Software Engineering,Shanghai,China,200092"}]},{"given":"Rongqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tongji University,School of Software Engineering,Shanghai,China,200092"}]},{"given":"Xiang","family":"Cheng","sequence":"additional","affiliation":[{"name":"Peking University,School of Electronics,Beijing,China,100871"}]}],"member":"263","reference":[{"key":"ref1","first-page":"530","article-title":"Multiagent traffic management: A reservation-based intersection control mechanism","volume-title":"Proc. 3rd Int. Jt. Conf. Auton. Agents Multiagent Syst. (AAMAS)","author":"Dresner"},{"key":"ref2","first-page":"59","article-title":"Time-to-collision and collision avoidance systems","author":"Van der Horst","year":"1994","journal-title":"Verkeersgedrag in Onderzoek"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/PERCOM.2008.72"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3161274"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3211272"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2940641"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2019.01.004"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3305321"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3250495"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3169907"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IV55152.2023.10186792"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM48099.2022.10001133"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3281367"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3200284"},{"key":"ref15","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","author":"Rashid"},{"key":"ref16","first-page":"24 611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"36th Adv. Neural Inf. Proces. Syst. (NIPS)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995816"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref19","first-page":"1046","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","volume-title":"Proc. 10th Int. Conf. Learn. Represent. (ICLR)","author":"Kuba"},{"article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. 4th Int. Conf. Learn. Represent. (ICLR)","author":"Schulman","key":"ref20"},{"key":"ref21","article-title":"An environment for autonomous driving decision-making","author":"Leurent","year":"2018","journal-title":"GitHub repository"}],"event":{"name":"2024 IEEE Intelligent Vehicle Symposium (IV)","start":{"date-parts":[[2024,6,2]]},"location":"Jeju Island, Korea, Republic of","end":{"date-parts":[[2024,6,5]]}},"container-title":["2024 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10587320\/10588370\/10588863.pdf?arnumber=10588863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,20]],"date-time":"2024-07-20T04:50:23Z","timestamp":1721451023000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10588863\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,2]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/iv55156.2024.10588863","relation":{},"subject":[],"published":{"date-parts":[[2024,6,2]]}}}