{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T16:59:14Z","timestamp":1780937954981,"version":"3.54.1"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2025AFD751"],"award-info":[{"award-number":["2025AFD751"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2024AFD411"],"award-info":[{"award-number":["2024AFD411"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2024AFD406"],"award-info":[{"award-number":["2024AFD406"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52302416"],"award-info":[{"award-number":["52302416"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.eswa.2026.132377","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T01:15:44Z","timestamp":1775438144000},"page":"132377","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Interpretable deep reinforcement learning with hybrid action space for cooperative ramp merging control"],"prefix":"10.1016","volume":"321","author":[{"given":"Li","family":"Song","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Zong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixuan","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9373-7399","authenticated-orcid":false,"given":"Xin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0926-9140","authenticated-orcid":false,"given":"Nengchao","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"David Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"10","key":"10.1016\/j.eswa.2026.132377_b0005","doi-asserted-by":"crossref","first-page":"6795","DOI":"10.1109\/TPAMI.2021.3103132","article-title":"Continuous Action Reinforcement Learning from a Mixture of Interpretable experts","volume":"44","author":"Akrour","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.132377_b0010","series-title":"2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)","first-page":"1611","article-title":"Vehicle Platooning Control for Merge Coordination: A Hybrid ACC-DMPC Approach","author":"An","year":"2022"},{"key":"10.1016\/j.eswa.2026.132377_b0015","unstructured":"Bester, C. J., James, S. D., & Konidaris, G. D. (2019). Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces (arXiv:1905.04388). arXiv. https:\/\/doi.org\/10.48550\/arXiv.1905.04388."},{"key":"10.1016\/j.eswa.2026.132377_b0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126938","article-title":"XLight: An interpretable multi-agent reinforcement learning approach for traffic signal control","volume":"273","author":"Cai","year":"2025","journal-title":"Expert Systems with Applications"},{"issue":"10","key":"10.1016\/j.eswa.2026.132377_b0025","doi-asserted-by":"crossref","first-page":"19213","DOI":"10.1109\/TITS.2022.3161535","article-title":"A Cooperative Merging Strategy for Connected and Automated Vehicles based on Game Theory with Transferable Utility","volume":"23","author":"Chen","year":"2022","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.eswa.2026.132377_b0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2021.103451","article-title":"Connected and automated vehicle distributed control for on-ramp merging scenario: A virtual rotation approach","volume":"133","author":"Chen","year":"2021","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"10.1016\/j.eswa.2026.132377_b0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2021.103220","article-title":"Optimizing the integrated off-ramp signal control to prevent queue spillback to the freeway mainline","volume":"128","author":"Chen","year":"2021","journal-title":"Transportation Research Part C: Emerging Technologies"},{"issue":"20","key":"10.1016\/j.eswa.2026.132377_b0045","doi-asserted-by":"crossref","first-page":"4459","DOI":"10.1016\/j.physa.2009.07.040","article-title":"Realizing Wardrop equilibria with real-time traffic information","volume":"388","author":"Davis","year":"2009","journal-title":"Physica A: Statistical Mechanics and Its Applications"},{"issue":"9","key":"10.1016\/j.eswa.2026.132377_b0050","doi-asserted-by":"crossref","first-page":"15298","DOI":"10.1109\/TITS.2022.3140219","article-title":"On-Ramp Merging strategies of Connected and Automated Vehicles considering Communication Delay","volume":"23","author":"Fang","year":"2022","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.eswa.2026.132377_b0055","doi-asserted-by":"crossref","first-page":"29577","DOI":"10.1109\/ACCESS.2025.3541042","article-title":"Hybrid CNN-LSTM and Proximal Policy Optimization Model for Traffic Light Control in a Multi-Agent Environment","volume":"13","author":"Faqir","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.132377_b0040","doi-asserted-by":"crossref","unstructured":"D. Frejo, J. R., Papamichail, I., Papageorgiou, M., & De Schutter, B. (2019). Macroscopic modeling of variable speed limits on freeways. Transportation Research Part C: Emerging Technologies, 100, 15\u201333. https:\/\/doi.org\/10.1016\/j.trc.2019.01.001.","DOI":"10.1016\/j.trc.2019.01.001"},{"key":"10.1016\/j.eswa.2026.132377_b0060","doi-asserted-by":"crossref","DOI":"10.1016\/j.trip.2025.101621","article-title":"A context-sensitive roadway classification framework for speed limit setting in the US","volume":"33","author":"Hsu","year":"2025","journal-title":"Transportation Research Interdisciplinary Perspectives"},{"issue":"3","key":"10.1016\/j.eswa.2026.132377_b0070","doi-asserted-by":"crossref","first-page":"592","DOI":"10.1049\/itr2.12286","article-title":"Improving traffic signal control operations using proximal policy optimization","volume":"17","author":"Huang","year":"2023","journal-title":"IET Intelligent Transport Systems"},{"issue":"10","key":"10.1016\/j.eswa.2026.132377_b0065","doi-asserted-by":"crossref","first-page":"18620","DOI":"10.1109\/TITS.2022.3157910","article-title":"A Roadside Decision-making Methodology based on Deep Reinforcement Learning to simultaneously Improve the Safety and Efficiency of Merging Zone","volume":"23","author":"Hu","year":"2022","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"2","key":"10.1016\/j.eswa.2026.132377_b0075","doi-asserted-by":"crossref","first-page":"249","DOI":"10.3390\/vehicles2020014","article-title":"Cooperative Highway Lane Merge of Connected Vehicles using Nonlinear Model Predictive Optimal Controller","volume":"2","author":"Hussain","year":"2020","journal-title":"Vehicles"},{"key":"10.1016\/j.eswa.2026.132377_b0080","series-title":"2025 International Conference on Multimedia Computing, Networking and Applications (MCNA)","first-page":"93","article-title":"A Game-Theoretic Approach for Dynamic Traffic Signal Control at Four-Way Intersections","author":"Ibtihal","year":"2025"},{"issue":"2","key":"10.1016\/j.eswa.2026.132377_b0085","doi-asserted-by":"crossref","first-page":"990","DOI":"10.3390\/s23020990","article-title":"Comparative Study of Cooperative Platoon Merging Control based on Reinforcement Learning","volume":"23","author":"Irshayyid","year":"2023","journal-title":"Sensors"},{"issue":"11","key":"10.1016\/j.eswa.2026.132377_b0090","doi-asserted-by":"crossref","first-page":"4234","DOI":"10.1109\/TITS.2019.2925871","article-title":"Cooperative Game Approach to Optimal Merging Sequence and on-Ramp Merging Control of Connected and Automated Vehicles","volume":"20","author":"Jing","year":"2019","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"8","key":"10.1016\/j.eswa.2026.132377_b0095","doi-asserted-by":"crossref","first-page":"12490","DOI":"10.1109\/TITS.2021.3114983","article-title":"Novel Decision-Making Strategy for Connected and Autonomous Vehicles in Highway On-Ramp Merging","volume":"23","author":"Kherroubi","year":"2022","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"1","key":"10.1016\/j.eswa.2026.132377_b0100","doi-asserted-by":"crossref","DOI":"10.1155\/2024\/5554608","article-title":"PID\u2010Based Freeway Work Zone Merge Control with Traffic State Prediction under mixed Traffic Flow of Connected Automated Vehicles and Manual Vehicles","volume":"2024","author":"Kim","year":"2024","journal-title":"Journal of Advanced Transportation"},{"key":"10.1016\/j.eswa.2026.132377_b0105","series-title":"2021 American Control Conference (ACC)","first-page":"2055","article-title":"Decentralized Cooperative Merging of Platoons of Connected and Automated Vehicles at Highway On-Ramps","author":"Kumaravel","year":"2021"},{"issue":"9","key":"10.1016\/j.eswa.2026.132377_b0125","doi-asserted-by":"crossref","first-page":"5746","DOI":"10.1109\/TSMC.2021.3131431","article-title":"Game Theory-based Ramp Merging for mixed Traffic with Unity-SUMO Co-simulation","volume":"52","author":"Liao","year":"2022","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"issue":"4","key":"10.1016\/j.eswa.2026.132377_b0110","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.1109\/TCCN.2020.3003036","article-title":"Deep Reinforcement Learning for Collaborative Edge Computing in Vehicular Networks","volume":"6","author":"Li","year":"2020","journal-title":"IEEE Transactions on Cognitive Communications and Networking"},{"issue":"6","key":"10.1016\/j.eswa.2026.132377_b0115","doi-asserted-by":"crossref","first-page":"6491","DOI":"10.1109\/TITS.2022.3221450","article-title":"Enhancing Cooperation of Vehicle Merging Control in Heavy Traffic using Communication-based Soft Actor-Critic Algorithm","volume":"24","author":"Li","year":"2023","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"7","key":"10.1016\/j.eswa.2026.132377_b0120","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1007\/s10489-025-06473-7","article-title":"Interpretable multi-agent reinforcement learning via multi-head variational autoencoders","volume":"55","author":"Li","year":"2025","journal-title":"Applied Intelligence"},{"key":"10.1016\/j.eswa.2026.132377_b0130","first-page":"7","article-title":"Anti-Jerk On-Ramp Merging using Deep Reinforcement Learning","volume":"2020","author":"Lin","year":"2020","journal-title":"IEEE Intelligent Vehicles Symposium (IV)"},{"issue":"24","key":"10.1016\/j.eswa.2026.132377_b0140","doi-asserted-by":"crossref","first-page":"39809","DOI":"10.1109\/JIOT.2024.3447039","article-title":"Reinforcement-Learning-based Multilane Cooperative Control for On-Ramp Merging in Mixed-Autonomy Traffic","volume":"11","author":"Liu","year":"2024","journal-title":"IEEE Internet of Things Journal"},{"issue":"13","key":"10.1016\/j.eswa.2026.132377_b0135","doi-asserted-by":"crossref","first-page":"1247","DOI":"10.1007\/s11227-025-07725-6","article-title":"Integrated control strategy for autonomous vehicle decision-making based on deep reinforcement learning","volume":"81","author":"Liu","year":"2025","journal-title":"The Journal of Supercomputing"},{"key":"10.1016\/j.eswa.2026.132377_b0145","series-title":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","first-page":"2575","article-title":"Microscopic Traffic simulation using SUMO","author":"Lopez","year":"2018"},{"key":"10.1016\/j.eswa.2026.132377_b0150","article-title":"A Unified Approach to Interpreting Model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"3","key":"10.1016\/j.eswa.2026.132377_b0155","doi-asserted-by":"crossref","first-page":"3129","DOI":"10.1109\/TITS.2022.3229477","article-title":"Mastering Arterial Traffic Signal Control with Multi-Agent Attention-based Soft Actor-Critic Model","volume":"24","author":"Mao","year":"2023","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.eswa.2026.132377_b0160","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2020\/2529856","article-title":"A Novel On-Ramp Merging Strategy for Connected and Automated Vehicles based on Game Theory","volume":"2020","author":"Min","year":"2020","journal-title":"Journal of Advanced Transportation"},{"key":"10.1016\/j.eswa.2026.132377_b0165","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2021.102987","article-title":"Integrated optimal control strategies for freeway traffic mixed with connected automated vehicles: A model-based reinforcement learning approach","volume":"123","author":"Pan","year":"2021","journal-title":"Transportation Research Part C: Emerging Technologies"},{"issue":"4","key":"10.1016\/j.eswa.2026.132377_b0170","doi-asserted-by":"crossref","first-page":"4731","DOI":"10.1109\/TITS.2025.3541955","article-title":"Model Predictive Control for On-Ramp Vehicle Merging to a Platoon on Main Road in Finite Time","volume":"26","author":"Qiang","year":"2025","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"10","key":"10.1016\/j.eswa.2026.132377_b0175","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1177\/0361198120935873","article-title":"Cooperative Highway Work Zone Merge Control based on Reinforcement Learning in a Connected and Automated Environment","volume":"2674","author":"Ren","year":"2020","journal-title":"Transportation Research Record: Journal of the Transportation Research Board"},{"key":"10.1016\/j.eswa.2026.132377_b0180","doi-asserted-by":"crossref","unstructured":"Ribeiro, M., Singh, S., & Guestrin, C. (2016). \u201cWhy Should I Trust You?\u201d: Explaining the Predictions of Any Classifier. In J. DeNero, M. Finlayson, & S. Reddy (Eds.), Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations (pp. 97\u2013101). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/N16-3020.","DOI":"10.18653\/v1\/N16-3020"},{"issue":"4","key":"10.1016\/j.eswa.2026.132377_b0185","doi-asserted-by":"crossref","first-page":"780","DOI":"10.1109\/TITS.2016.2587582","article-title":"Automated and Cooperative Vehicle Merging at Highway On-Ramps","volume":"18","author":"Rios-Torres","year":"2017","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.eswa.2026.132377_b0190","first-page":"3567","article-title":"Reinforcement Learning with Explainability for Traffic Signal Control","volume":"2019","author":"Rizzo","year":"2019","journal-title":"IEEE Intelligent Transportation Systems Conference (ITSC)"},{"issue":"6","key":"10.1016\/j.eswa.2026.132377_b0195","doi-asserted-by":"crossref","first-page":"1051","DOI":"10.1049\/itr2.12337","article-title":"Modelling and simulation of (connected) autonomous vehicles longitudinal driving behavior: A state-of-the-art","volume":"17","author":"Sadid","year":"2023","journal-title":"IET Intelligent Transport Systems"},{"key":"10.1016\/j.eswa.2026.132377_b0205","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128180","article-title":"Exploring the feasibility and sensitivity of deep reinforcement learning controlled traffic signals in bidirectional two-lane road work zones","volume":"287","author":"Song","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132377_b0200","doi-asserted-by":"crossref","unstructured":"Song, L., Li, S., Chen, G., Zhao, X., Lyu, N., & Fan, W. (David). (2026). Exploring mechanisms of integrating global perception prediction for connected vehicles with lane-specific reinforcement learning-based variable speed limits. Expert Systems with Applications, 299, 129958. https:\/\/doi.org\/10.1016\/j.eswa.2025.129958.","DOI":"10.1016\/j.eswa.2025.129958"},{"key":"10.1016\/j.eswa.2026.132377_b0210","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2022.103650","article-title":"A novel hierarchical cooperative merging control model of connected and automated vehicles featuring flexible merging positions in system optimization","volume":"138","author":"Tang","year":"2022","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"10.1016\/j.eswa.2026.132377_b0215","series-title":"2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC)","first-page":"1","article-title":"Formulation of deep reinforcement learning architecture toward autonomous driving for on-ramp merge","author":"Wang","year":"2017"},{"key":"10.1016\/j.eswa.2026.132377_b0220","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2020.102649","article-title":"Differential variable speed limits control for freeway recurrent bottlenecks via deep actor-critic algorithm","volume":"117","author":"Wu","year":"2020","journal-title":"Transportation Research Part C: Emerging Technologies"},{"issue":"11","key":"10.1016\/j.eswa.2026.132377_b0230","doi-asserted-by":"crossref","first-page":"21821","DOI":"10.1109\/TITS.2022.3175967","article-title":"A Platoon-based Hierarchical Merging Control for On-Ramp Vehicles under Connected Environment","volume":"23","author":"Xue","year":"2022","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"4","key":"10.1016\/j.eswa.2026.132377_b0225","doi-asserted-by":"crossref","first-page":"252","DOI":"10.3390\/machines12040252","article-title":"Safe Hybrid-Action Reinforcement Learning-based Decision and Control for Discretionary Lane Change","volume":"12","author":"Xu","year":"2024","journal-title":"Machines"},{"key":"10.1016\/j.eswa.2026.132377_b0240","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1016\/j.trc.2017.11.019","article-title":"Integration of adaptive signal control and freeway off-ramp priority control for commuting corridors","volume":"86","author":"Yang","year":"2018","journal-title":"Transportation Research Part C: Emerging Technologies"},{"issue":"2","key":"10.1016\/j.eswa.2026.132377_b0235","doi-asserted-by":"crossref","first-page":"1014","DOI":"10.1109\/TSMC.2023.3312411","article-title":"Leveraging Reward Consistency for Interpretable Feature Discovery in Reinforcement Learning","volume":"54","author":"Yang","year":"2024","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"issue":"4","key":"10.1016\/j.eswa.2026.132377_b0245","doi-asserted-by":"crossref","first-page":"1258","DOI":"10.1109\/TCST.2024.3477354","article-title":"Automated Lane Merging via Game Theory and Branch Model Predictive Control","volume":"33","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Control Systems Technology"},{"key":"10.1016\/j.eswa.2026.132377_b0250","doi-asserted-by":"crossref","DOI":"10.1016\/j.chaos.2025.116548","article-title":"A lattice hydrodynamic model for on-ramp and off-ramp traffic flow considering non-equilibrium characteristics and heterogeneous mixed-flow speed delay","volume":"198","author":"Zhao","year":"2025","journal-title":"Chaos, Solitons & Fractals"},{"key":"10.1016\/j.eswa.2026.132377_b0255","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2024.104807","article-title":"Reasoning graph-based reinforcement learning to cooperate mixed connected and autonomous traffic at unsignalized intersections","volume":"167","author":"Zhou","year":"2024","journal-title":"Transportation Research Part C: Emerging Technologies"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095741742601290X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095741742601290X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T16:10:47Z","timestamp":1780935047000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095741742601290X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":51,"alternative-id":["S095741742601290X"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132377","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Interpretable deep reinforcement learning with hybrid action space for cooperative ramp merging control","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132377","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132377"}}