{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T15:43:13Z","timestamp":1792597393561,"version":"4.5.0"},"reference-count":38,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin Municipality","doi-asserted-by":"publisher","award":["23JCQNJC01780"],"award-info":[{"award-number":["23JCQNJC01780"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011343","name":"Key Laboratory of System Control and Information Processing, Ministry of Education","doi-asserted-by":"publisher","award":["Scip20240116"],"award-info":[{"award-number":["Scip20240116"]}],"id":[{"id":"10.13039\/501100011343","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62403350"],"award-info":[{"award-number":["62403350"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62403348"],"award-info":[{"award-number":["62403348"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004517","name":"Tianjin University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004517","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neucom.2026.134707","type":"journal-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T06:01:28Z","timestamp":1785996088000},"page":"134707","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Hierarchical soft actor-critic with auxiliary value function guidance for urban autonomous driving"],"prefix":"10.1016","volume":"703","author":[{"given":"Zhiqiang","family":"Zuo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenfei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2920-6251","authenticated-orcid":false,"given":"Haoyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yijing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"9","key":"10.1016\/j.neucom.2026.134707_bib0005","first-page":"1507","article-title":"A survey of motion control for unmanned ground vehicles","volume":"41","author":"Wang","year":"2024","journal-title":"Control Theory Appl."},{"issue":"1","key":"10.1016\/j.neucom.2026.134707_bib0010","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1109\/TIV.2023.3318070","article-title":"Recent advancements in end-to-end autonomous driving using deep learning: a survey","volume":"9","author":"Chib","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.neucom.2026.134707_bib0015","series-title":"International Conference on Artificial Intelligence and Autonomous Robot Systems","first-page":"187","article-title":"Automatic driving decision model based on deep reinforcement learning algorithms in complex environments","author":"Wang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134707_bib0020","series-title":"International Conference on Electronics, Information, and Communication","first-page":"1","article-title":"Enhancing autonomous driving with pre-trained imitation and reinforcement learning","author":"Choi","year":"2025"},{"key":"10.1016\/j.neucom.2026.134707_bib0025","series-title":"China Automation Congress","first-page":"8648","article-title":"Lane-changing decisions making for autonomous vehicles via behavior cloning and decision tree","author":"Guo","year":"2023"},{"key":"10.1016\/j.neucom.2026.134707_bib0030","doi-asserted-by":"crossref","first-page":"12134","DOI":"10.1109\/TASE.2025.3539340","article-title":"Safe and interpretable human-like planning with transformer-based deep inverse reinforcement learning for autonomous driving","volume":"22","author":"Nan","year":"2025","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.neucom.2026.134707_bib0035","series-title":"IEEE 95th Vehicular Technology Conference","first-page":"1","article-title":"An analysis of distributional shifts in automated driving functions in highway scenarios","author":"Candido","year":"2022"},{"key":"10.1016\/j.neucom.2026.134707_bib0040","series-title":"Global Conference on Communications and Information Technologies","first-page":"1","article-title":"Reinforcement learning advances in autonomous driving: a detailed examination of DQN and PPO","author":"Sharma","year":"2024"},{"key":"10.1016\/j.neucom.2026.134707_bib0045","series-title":"IEEE International Conference on Consumer Electronics","first-page":"1","article-title":"Performance analysis of RL based end-to-end learning technology for autonomous driving","author":"Jun","year":"2025"},{"key":"10.1016\/j.neucom.2026.134707_bib0050","series-title":"4th International Conference on Artificial Intelligence, Internet and Digital Economy","first-page":"279","article-title":"TSAC: transformer-based soft actor-critic for behavior decision-making in autonomous driving","author":"Gao","year":"2025"},{"key":"10.1016\/j.neucom.2026.134707_bib0055","series-title":"IEEE International Conference on Unmanned Systems","first-page":"37","article-title":"A distributional soft-actor-critic-discrete-based decision-making algorithm for autonomous driving","author":"Mao","year":"2023"},{"key":"10.1016\/j.neucom.2026.134707_bib0060","series-title":"IEEE International Conference on Advanced Networks and Telecommunications Systems","first-page":"1","article-title":"Adaptive trajectory planning in autonomous vehicles: a hierarchical reinforcement learning approach with soft actor-critic","author":"Sharma","year":"2024"},{"key":"10.1016\/j.neucom.2026.134707_bib0065","series-title":"IEEE Integration of Stochastic Energy in Power Systems Workshop","first-page":"3","article-title":"Reliability modeling with hidden Markov and semi-Markov chains","author":"Barbu","year":"2013"},{"issue":"4","key":"10.1016\/j.neucom.2026.134707_bib0070","doi-asserted-by":"crossref","first-page":"5018","DOI":"10.1109\/TITS.2025.3536020","article-title":"Dynamic option policy enabled hierarchical deep reinforcement learning model for autonomous overtaking maneuver","volume":"26","author":"Singh Lodhi","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"12","key":"10.1016\/j.neucom.2026.134707_bib0075","doi-asserted-by":"crossref","first-page":"19522","DOI":"10.1109\/TITS.2024.3457776","article-title":"Imagination-augmented hierarchical reinforcement learning for safe and interactive autonomous driving in urban environments","volume":"25","author":"Lee","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.neucom.2026.134707_bib0080","series-title":"International Joint Conference on Neural Networks","first-page":"1","article-title":"Hierarchical reinforcement learning-based policy switching towards multi-scenarios autonomous driving","author":"Guo","year":"2021"},{"issue":"12","key":"10.1016\/j.neucom.2026.134707_bib0085","doi-asserted-by":"crossref","first-page":"19605","DOI":"10.1109\/TITS.2024.3458439","article-title":"Risk-anticipatory autonomous driving strategies considering vehicles\u2019 weights based on hierarchical deep reinforcement learning","volume":"25","author":"Chen","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"9","key":"10.1016\/j.neucom.2026.134707_bib0090","doi-asserted-by":"crossref","first-page":"9966","DOI":"10.1109\/TITS.2023.3271642","article-title":"Safe-state enhancement method for autonomous driving via direct hierarchical reinforcement learning","volume":"24","author":"Gu","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"7","key":"10.1016\/j.neucom.2026.134707_bib0095","doi-asserted-by":"crossref","first-page":"3680","DOI":"10.1109\/TNNLS.2021.3116063","article-title":"Deep reinforcement learning on autonomous driving policy with auxiliary critic network","volume":"34","author":"Wu","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"3","key":"10.1016\/j.neucom.2026.134707_bib0100","doi-asserted-by":"crossref","first-page":"7513","DOI":"10.1109\/TTE.2023.3332345","article-title":"Complex network cognition-based federated reinforcement learning for end-to-end urban autonomous driving","volume":"10","author":"Cai","year":"2024","journal-title":"IEEE Trans. Transp. Electrif."},{"issue":"12","key":"10.1016\/j.neucom.2026.134707_bib0105","first-page":"4466","article-title":"Learning to drive in a day","volume":"20","author":"Kendall","year":"2019","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.neucom.2026.134707_bib0110","first-page":"1","article-title":"Semi-Markov options enabled DDPG method for autonomous vehicle overtaking with LiDAR and RADAR fusion","author":"Lodhi","year":"2025","journal-title":"IEEE Trans. Mob. Comput."},{"issue":"2","key":"10.1016\/j.neucom.2026.134707_bib0115","article-title":"Deep reinforcement learning lane-change decision-making for autonomous vehicles based on motion primitives library in hierarchical action space","volume":"1","author":"Jin","year":"2024","journal-title":"Artif. Intell. Auton. Syst."},{"key":"10.1016\/j.neucom.2026.134707_bib0120","series-title":"Technological Innovation for AI-Powered Cyber-Physical Systems","first-page":"238","article-title":"Autonomous vehicle decision making through multi-grid Markov decision processes","author":"Caldeira","year":"2025"},{"key":"10.1016\/j.neucom.2026.134707_bib0125","doi-asserted-by":"crossref","first-page":"1662","DOI":"10.3389\/fnbot.2025.1451923","article-title":"A survey of decision-making and planning methods for self-driving vehicles","volume":"19","author":"Hu","year":"2025","journal-title":"Front. Neurorobotics"},{"key":"10.1016\/j.neucom.2026.134707_bib0130","first-page":"1","article-title":"Reinforcement learning with unsupervised auxiliary tasks","volume":"57","author":"Jaderberg","year":"2017","journal-title":"J. Artif. Intell. Res."},{"key":"10.1016\/j.neucom.2026.134707_bib0135","first-page":"1","article-title":"A deeper look at planning as learning from replay","volume":"242","author":"van Seijen","year":"2017","journal-title":"Artif. Intell."},{"key":"10.1016\/j.neucom.2026.134707_bib0140","doi-asserted-by":"crossref","first-page":"2296","DOI":"10.3389\/frobt.2024.1444188","article-title":"HPRS: hierarchical potential-based reward shaping from task specifications","volume":"11","author":"Berducci","year":"2025","journal-title":"Front. Robot. AI"},{"issue":"5","key":"10.1016\/j.neucom.2026.134707_bib0145","doi-asserted-by":"crossref","first-page":"3955","DOI":"10.1109\/TPAMI.2024.3352811","article-title":"MTR++ multi-agent motion prediction with symmetric scene modeling and guided intention querying","volume":"46","author":"Shi","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134707_bib0150","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/j.future.2024.03.057","article-title":"Potential-based reward shaping using state\u2013space segmentation for efficiency in reinforcement learning","volume":"157","author":"Bal","year":"2024","journal-title":"Future Gener. Comput. Syst."},{"issue":"184","key":"10.1016\/j.neucom.2026.134707_bib0155","article-title":"Hierarchical reinforcement learning from demonstration via reachability-based reward shaping","volume":"56","author":"Gao","year":"2024","journal-title":"Neural Process. Lett."},{"issue":"11","key":"10.1016\/j.neucom.2026.134707_bib0160","article-title":"Reward shaping using directed graph convolution neural networks for reinforcement learning and games","volume":"11","author":"Sang","year":"2023","journal-title":"Front. Phys."},{"key":"10.1016\/j.neucom.2026.134707_bib0165","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevResearch.5.023085","article-title":"Entropy regularized reinforcement learning using large deviation theory","volume":"5","author":"Arriojas","year":"2023","journal-title":"Phys. Rev. Res."},{"issue":"3","key":"10.1016\/j.neucom.2026.134707_bib0170","doi-asserted-by":"crossref","first-page":"3461","DOI":"10.1109\/TPAMI.2022.3190471","article-title":"Metadrive: composing diverse driving scenarios for generalizable reinforcement learning","volume":"45","author":"Li","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"7","key":"10.1016\/j.neucom.2026.134707_bib0175","doi-asserted-by":"crossref","DOI":"10.3390\/fi16070238","article-title":"Enhancing autonomous driving navigation using soft actor-critic","volume":"16","author":"Elallid","year":"2024","journal-title":"Future Internet"},{"key":"10.1016\/j.neucom.2026.134707_bib0180","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1109\/OJITS.2023.3300748","article-title":"A hierarchical framework for multi-lane autonomous driving based on reinforcement learning","volume":"4","author":"Zhang","year":"2023","journal-title":"IEEE Open J. Intell. Transp. Syst."},{"issue":"8","key":"10.1016\/j.neucom.2026.134707_bib0185","doi-asserted-by":"crossref","first-page":"10902","DOI":"10.1109\/TITS.2021.3096998","article-title":"Hierarchical program-triggered reinforcement learning agents for automated driving","volume":"23","author":"Gangopadhyay","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"12","key":"10.1016\/j.neucom.2026.134707_bib0190","doi-asserted-by":"crossref","first-page":"19365","DOI":"10.1109\/TITS.2024.3452480","article-title":"A survey on recent advancements in autonomous driving using deep reinforcement learning: applications, challenges, and solutions","volume":"25","author":"Zhao","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226021053?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226021053?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T14:48:17Z","timestamp":1792594097000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226021053"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":38,"alternative-id":["S0925231226021053"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134707","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Hierarchical soft actor-critic with auxiliary value function guidance for urban autonomous driving","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134707","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"134707"}}