{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T10:52:26Z","timestamp":1786099946351,"version":"3.56.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key R&D Project of Zhejiang Province","award":["2024C01172"],"award-info":[{"award-number":["2024C01172"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Systems Journal"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/jsyst.2025.3528976","type":"journal-article","created":{"date-parts":[[2025,2,3]],"date-time":"2025-02-03T13:27:08Z","timestamp":1738589228000},"page":"317-326","source":"Crossref","is-referenced-by-count":10,"title":["Learning to Model Diverse Driving Behaviors in Highly Interactive Autonomous Driving Scenarios With Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2496-7748","authenticated-orcid":false,"given":"Weiwei","family":"Liu","sequence":"first","affiliation":[{"name":"The Advanced Perception on Robotics and Intelligent Learning Lab, College of Control Science and Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxuan","family":"Hu","sequence":"additional","affiliation":[{"name":"Huzhou Institute of Zhejiang University, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3286-5925","authenticated-orcid":false,"given":"Wei","family":"Jing","sequence":"additional","affiliation":[{"name":"Autonomous Driving Lab, Alibaba DAMO Academy, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lanxin","family":"Lei","sequence":"additional","affiliation":[{"name":"Autonomous Driving Lab, Alibaba DAMO Academy, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingping","family":"Gao","sequence":"additional","affiliation":[{"name":"Autonomous Driving Lab, Alibaba DAMO Academy, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4822-8939","authenticated-orcid":false,"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"The Advanced Perception on Robotics and Intelligent Learning Lab, College of Control Science and Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015"},{"key":"ref2","first-page":"1","article-title":"Multiagent bidirectionally-coordinated nets for learning to play starcraft combat games","volume-title":"Proc. Workshop Neural Inf. Process. Syst.","author":"Peng","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47358-7_7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636442"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s43684-022-00023-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3303408"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207663"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/832"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/math10091551"},{"key":"ref10","article-title":"Reward machines for cooperative multi-agent reinforcement learning","author":"Neary","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2019.1900120"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2020.105908"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562006"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3356464.3357712"},{"key":"ref15","first-page":"2107","article-title":"Using reward machines for high-level task specification and decomposition in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Icarte","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00291"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3320496.3320500"},{"key":"ref18","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref19","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. 31st Int. Conf. Mach. Learn.","author":"Silver","year":"2014"},{"key":"ref20","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref21","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref22","article-title":"Is independent learning all you need in the starcraft multi-agent challenge?","author":"de Witt","year":"2020"},{"key":"ref23","article-title":"The surprising effectiveness of PPO in cooperative, multi-agent games","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Yu","year":"2022"},{"key":"ref24","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","author":"Lowe","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114726"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1142\/S0219525901000188"},{"key":"ref27","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. 17th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Sunehag","year":"2018"},{"issue":"1","key":"ref28","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/1025349"},{"key":"ref31","first-page":"118","article-title":"An action selection method using degree of cooperation in a multi-agent system","volume-title":"Proc. Int. Conf. Artif. Life Robot.","author":"Kawamura","year":"2014"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-014-9265-1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561071"},{"key":"ref34","article-title":"End-to-end deep reinforcement learning for lane keeping assist","author":"Sallab","year":"2016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500556"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2106158"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2893683"},{"key":"ref38","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"Shalev-Shwartz","year":"2016"},{"key":"ref39","first-page":"64","article-title":"Optimality and approximation with policy gradient methods in Markov decision processes","volume-title":"Proc. 33rd Conf. Learn. Theory","author":"Agarwal","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref41","first-page":"11853","article-title":"Learning implicit credit assignment for cooperative multi-agent reinforcement learning","volume":"33","author":"Zhou","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref42","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Iqbal","year":"2019"},{"key":"ref43","first-page":"3053","article-title":"RLlib: Abstractions for distributed reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Liang","year":"2018"},{"key":"ref44","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Yang","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"}],"container-title":["IEEE Systems Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4267003\/10929683\/10869517.pdf?arnumber=10869517","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T20:58:52Z","timestamp":1769201932000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10869517\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":45,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/jsyst.2025.3528976","relation":{},"ISSN":["1932-8184","1937-9234","2373-7816"],"issn-type":[{"value":"1932-8184","type":"print"},{"value":"1937-9234","type":"electronic"},{"value":"2373-7816","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}