{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T02:02:07Z","timestamp":1777514527972,"version":"3.51.4"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10341803","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"5507-5513","source":"Crossref","is-referenced-by-count":5,"title":["A Two-Stage Based Social Preference Recognition in Multi-Agent Autonomous Driving System"],"prefix":"10.1109","author":[{"given":"Jintao","family":"Xue","sequence":"first","affiliation":[{"name":"Zhejiang University,Dept of Information Science and Electronic Engineering,Hangzhou,China"}]},{"given":"Dongkun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Dept of Control Science and Engineering,Hangzhou,China"}]},{"given":"Rong","family":"Xiong","sequence":"additional","affiliation":[{"name":"Zhejiang University,Dept of Control Science and Engineering,Hangzhou,China"}]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Dept of Control Science and Engineering,Hangzhou,China"}]},{"given":"Eryun","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University,Dept of Information Science and Electronic Engineering,Hangzhou,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tro.2021.3087314"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"},{"key":"ref4","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"Shalev-Shwartz","year":"2016","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207663"},{"key":"ref6","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"},{"key":"ref7","article-title":"Altruistic maneuver planning for cooperative autonomous vehicles using multi-agent advantage actor-critic","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops","author":"Toghi","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1820676116"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3102407"},{"key":"ref10","first-page":"1","article-title":"Multi-agent graph reinforcement learning for connected automated driving","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML)","author":"Wang","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2310"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636151"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3207872"},{"key":"ref14","article-title":"Socially-attentive policy optimization in multi-agent self-driving system","volume-title":"6th Annual Conference on Robot Learning","author":"Dai"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197132"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3152594"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061350"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3088935"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593969"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2022.3189836"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564702"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3191241"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636849"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995726"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147924"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3074880"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967997"},{"key":"ref29","article-title":"Revisiting parameter sharing in multi-agent deep reinforcement learning","author":"Terry","year":"2020","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01154"},{"key":"ref31","article-title":"Deep sets","volume":"30","author":"Zaheer","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref33","first-page":"718","article-title":"Urban driver: Learning to drive from real-world demonstrations using policy gradients","volume-title":"Conference on Robot Learning","author":"Scheel"},{"key":"ref34","volume-title":"Universe","author":"Zhang","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref36","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR (Poster)"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10341803.pdf?arnumber=10341803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:49:30Z","timestamp":1705027770000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341803\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341803","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}