{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T12:43:54Z","timestamp":1730292234100,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T00:00:00Z","timestamp":1689552000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T00:00:00Z","timestamp":1689552000000},"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":[[2023,7,17]]},"DOI":"10.1109\/rcar58764.2023.10249648","type":"proceedings-article","created":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T17:36:59Z","timestamp":1695231419000},"page":"372-377","source":"Crossref","is-referenced-by-count":2,"title":["Mastering Cooperative Driving Strategy in Complex Scenarios using Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Qingyi","family":"Liang","sequence":"first","affiliation":[{"name":"Southern University of Science and Technology,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengmin","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwen","family":"Yin","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Xu","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongming","family":"Pan","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaobo","family":"Dang","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Liu","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"son","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref24","first-page":"69","article-title":"Estimation of Road Geometric Information for Congested Roads by Autonomous Driving","volume":"9","author":"li","year":"2020","journal-title":"Integration Technology"},{"key":"ref12","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"rashid","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref23","article-title":"Deep Dense Network-Based Curriculum Reinforcement Learning for High-Speed Overtaking","author":"liu","year":"2022","journal-title":"IEEE Intelligent Transportation Systems Magazine"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1037\/h0023986"},{"key":"ref14","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"article-title":"Value-decomposition networks for cooperative multi-agent learning","year":"2017","author":"sunehag","key":"ref11"},{"key":"ref22","article-title":"The surprising effectiveness of ppo in cooperative, multi-agent games","author":"yu","year":"2021","journal-title":"Arxiv preprint arXiv"},{"key":"ref10","first-page":"10784","article-title":"Learning to simulate self-driven particles system with coordinated policy optimization","volume":"34","author":"peng","year":"2021","journal-title":"Advances in neural information processing systems"},{"article-title":"Is independent learning all you need in the starcraft multi-agent challenge?","year":"2020","author":"de witt","key":"ref21"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/per.2410020304"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811626"},{"article-title":"Altruistic maneuver planning for cooperative autonomous vehicles using multi-agent advantage actor-critic","year":"2021","author":"toghi","key":"ref18"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636151"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1820676116"},{"article-title":"Accelerating Reinforcement Learning for Autonomous Driving using Task-Agnostic and Ego-Centric Motion Skills","year":"2022","author":"zhou","key":"ref9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.add4679"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9746-1"},{"article-title":"Dota 2 with large scale deep reinforcement learning","year":"2019","author":"berner","key":"ref5"}],"event":{"name":"2023 IEEE International Conference on Real-time Computing and Robotics (RCAR)","start":{"date-parts":[[2023,7,17]]},"location":"Datong, China","end":{"date-parts":[[2023,7,20]]}},"container-title":["2023 IEEE International Conference on Real-time Computing and Robotics (RCAR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10249208\/10249018\/10249648.pdf?arnumber=10249648","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T18:07:45Z","timestamp":1696874865000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10249648\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,17]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/rcar58764.2023.10249648","relation":{},"subject":[],"published":{"date-parts":[[2023,7,17]]}}}