{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T17:59:35Z","timestamp":1770227975484,"version":"3.49.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"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","award":["62303390"],"award-info":[{"award-number":["62303390"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Key Lab of Integrated Communication, Sensing and Computation for Ubiquitous Internet of Things","award":["2023B1212010007"],"award-info":[{"award-number":["2023B1212010007"]}]},{"name":"Guangzhou-HKUST(GZ) Joint Funding Scheme","award":["2024A03J0618"],"award-info":[{"award-number":["2024A03J0618"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Veh."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tiv.2024.3470910","type":"journal-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T13:30:56Z","timestamp":1727703056000},"page":"4010-4025","source":"Crossref","is-referenced-by-count":4,"title":["Game-Theoretic Driver Modeling and Decision-Making for Autonomous Driving With Temporal-Spatial Attention-Based Deep Q-Learning"],"prefix":"10.1109","volume":"10","author":[{"given":"Xiao","family":"Zhou","sequence":"first","affiliation":[{"name":"Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1801-4297","authenticated-orcid":false,"given":"Zengqi","family":"Peng","sequence":"additional","affiliation":[{"name":"Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6735-2866","authenticated-orcid":false,"given":"Yusen","family":"Xie","sequence":"additional","affiliation":[{"name":"Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4500-238X","authenticated-orcid":false,"given":"Ming","family":"Liu","sequence":"additional","affiliation":[{"name":"Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9405-8232","authenticated-orcid":false,"given":"Jun","family":"Ma","sequence":"additional","affiliation":[{"name":"Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3224912"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3189836"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3274536"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3395479"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968225"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3389827"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3332080"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564423"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2012.6232131"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422594"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3151651"},{"key":"ref14","article-title":"Social attention for autonomous decision-making in dense traffic","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst. Mach. Learn. Auton. Driving Workshop","author":"Leurent","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102615"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2820002"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2014.2357038"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3227738"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2019.0317"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3088935"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341803"},{"key":"ref22","first-page":"10784","article-title":"Learning to simulate self-driven particles system with coordinated policy optimization","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Peng","year":"2021"},{"key":"ref23","first-page":"946","article-title":"Socially-attentive policy optimization in multi-agent self-driving system","volume-title":"Proc. Conf. Robot Learn.","author":"Dai"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47358-7_7"},{"key":"ref25","first-page":"264","article-title":"SMARTS: Scalable multi-agent reinforcement learning training school for autonomous driving","volume-title":"Proc. Conf. Robot Learn.","author":"Zhou","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2017.2723574"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/s21041523"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3323138"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3321346"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794007"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3036984"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2016.7525162"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917314"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3134249"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8815251"},{"key":"ref36","article-title":"Dealing with non-stationarity in MARL via trust-region decomposition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2022"},{"key":"ref37","volume-title":"Game Theory","author":"Fudenberg","year":"1991"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995816"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/robot.2010.5509799"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s00182-023-00837-4"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC58415.2024.10919682"},{"key":"ref42","article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jang","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8430842"},{"key":"ref44","article-title":"An environment for autonomous driving decision-making","author":"Leurent","year":"2018"},{"issue":"268","key":"ref45","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref46","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref47","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref48","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013"}],"container-title":["IEEE Transactions on Intelligent Vehicles"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7274857\/11205917\/10700678.pdf?arnumber=10700678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T04:41:17Z","timestamp":1760676077000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10700678\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":48,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tiv.2024.3470910","relation":{},"ISSN":["2379-8904","2379-8858"],"issn-type":[{"value":"2379-8904","type":"electronic"},{"value":"2379-8858","type":"print"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}