{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T05:39:42Z","timestamp":1773121182898,"version":"3.50.1"},"reference-count":53,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72471023"],"award-info":[{"award-number":["72471023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers & Industrial Engineering"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.cie.2025.111784","type":"journal-article","created":{"date-parts":[[2025,12,25]],"date-time":"2025-12-25T16:00:14Z","timestamp":1766678414000},"page":"111784","update-policy":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["A deep reinforcement learning approach for integrated optimization of train scheduling and rolling stock circulation planning"],"prefix":"10.1016","volume":"213","author":[{"ORCID":"https:\/\/linproxy.fan.workers.dev:443\/https\/orcid.org\/0009-0005-1916-9871","authenticated-orcid":false,"given":"Xiaoli","family":"Zhao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/linproxy.fan.workers.dev:443\/https\/orcid.org\/0000-0003-3738-029X","authenticated-orcid":false,"given":"Dewei","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/linproxy.fan.workers.dev:443\/https\/orcid.org\/0009-0009-7182-4596","authenticated-orcid":false,"given":"Xinyu","family":"Bao","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.cie.2025.111784_b0005","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1287\/trsc.1060.0155","article-title":"Efficient circulation of railway rolling stock","volume":"40","author":"Alfieri","year":"2006","journal-title":"Transportation Science"},{"key":"10.1016\/j.cie.2025.111784_b0015","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1016\/j.trb.2014.08.013","article-title":"Single-line rail rapid transit timetabling under dynamic passenger demand","volume":"70","author":"Barrena","year":"2014","journal-title":"Transportation Research Part B: Methodological"},{"key":"10.1016\/j.cie.2025.111784_b0020","series-title":"Reinforcement learning and optimal control (1)","author":"Bertsekas","year":"2019"},{"key":"10.1016\/j.cie.2025.111784_b0025","unstructured":"Berner, C., Brockman, G., Chan, B., Cheung, V., Debiak, P., Dennison, C., Farhi, D., Fischer, Q., Hashme, S., Hesse, C., Jozefowicz, R., Gray, S., Olsson, C., Pachocki, J. W., Petrov, M., de Oliveira Pinto, H. P., Raiman, J., Salimans, T., Schlatter, J., Schneider, J., Sidor, S., Sutskever, I., Tang, J., Wolski, F., Zhang, S. (2019). Dota 2 with large scale deep reinforcement learning. ArXiv :1912.06680."},{"key":"10.1016\/j.cie.2025.111784_b0045","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1007\/s10479-011-0978-0","article-title":"Integration of timetable planning and rolling stock in rapid transit networks","volume":"199","author":"Cadarso","year":"2012","journal-title":"Ann. Oper. Res."},{"key":"10.1016\/j.cie.2025.111784_bib301","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1016\/j.trb.2018.09.013","article-title":"The railway rapid transit frequency setting problem with speed-dependent operation costs","volume":"117","author":"Canca","year":"2018","journal-title":"Transportation Research Part B: Methodological"},{"key":"10.1016\/j.cie.2025.111784_b0050","doi-asserted-by":"crossref","first-page":"680","DOI":"10.1016\/j.trpro.2014.10.047","article-title":"A rolling stock circulation model for railway rapid transit systems","volume":"3","author":"Canca","year":"2014","journal-title":"Transportation Research Procedia"},{"issue":"3","key":"10.1016\/j.cie.2025.111784_b0055","first-page":"746","article-title":"An effective peak period heuristic for railway rolling stock planning","volume":"53","author":"Cacchiani","year":"2019","journal-title":"Transportation Science"},{"key":"10.1016\/j.cie.2025.111784_b0065","unstructured":"Dulac-Arnold, G., Evans, R., van Hasselt, H., Sunehag, P., Lillicrap, T., Hunt, J., Mann, T., Weber, T., Degris, T., Coppin, B. Deep reinforcement learning in large discrete action spaces. (2015). arXiv preprint arXiv:1512.07679."},{"key":"10.1016\/j.cie.2025.111784_b0070","article-title":"Intelligent scheduling of urban rail transit loop line trains: A study on coordinated optimization of timetables and rolling stock circulation plans based on DQN deep reinforcement learning","volume":"111297","author":"Dong","year":"2025","journal-title":"Computers & Industrial Engineering"},{"key":"10.1016\/j.cie.2025.111784_b0075","doi-asserted-by":"crossref","unstructured":"Fan, Z., Su, R., Zhang, W., Yu, Y. (2019). Hybrid actor-critic reinforcement learning in parameterized action space. arXiv:1903.01344.","DOI":"10.24963\/ijcai.2019\/316"},{"key":"10.1016\/j.cie.2025.111784_b0080","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2024.104756","article-title":"Integrated optimization of train timetabling and rolling stock circulation problem with flexible short-turning and energy-saving strategies","volume":"166","author":"Gong","year":"2024","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"10.1016\/j.cie.2025.111784_b0085","unstructured":"Hausknecht, M., Stone, P. (2015). Deep reinforcement learning in parameterized action space. In Proceedings of the International Conference on Learning Representations (ICLR), 2016."},{"key":"10.1016\/j.cie.2025.111784_b0090","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2307\/1913641","article-title":"Bayesian estimates of equation system parameters: An application of integration by Monte Carlo","author":"Kloek","year":"1978","journal-title":"Econometrica: Journal of the Econometric Society"},{"issue":"2","key":"10.1016\/j.cie.2025.111784_b0095","doi-asserted-by":"crossref","first-page":"727","DOI":"10.1109\/TITS.2018.2829165","article-title":"A scalable reinforcement learning algorithm for scheduling railway lines","volume":"20","author":"Khadilkar","year":"2018","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.cie.2025.111784_b0100","doi-asserted-by":"crossref","DOI":"10.1016\/j.omega.2018.10.020","article-title":"Collaborative optimization for metro train scheduling and train connections combined with passenger flow control strategy","volume":"90","author":"Liu","year":"2020","journal-title":"Omega"},{"issue":"4","key":"10.1016\/j.cie.2025.111784_b0105","doi-asserted-by":"crossref","first-page":"3096","DOI":"10.1109\/TTE.2021.3075462","article-title":"A deep reinforcement learning approach for the energy-aimed train timetable rescheduling problem under disturbances","volume":"7","author":"Liao","year":"2021","journal-title":"IEEE Transactions on Transportation Electrification"},{"key":"10.1016\/j.cie.2025.111784_b0110","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1016\/j.trb.2022.02.006","article-title":"Train timetabling with the general learning environment and multi-agent deep reinforcement learning","volume":"157","author":"Li","year":"2022","journal-title":"Transportation Research Part B: Methodological"},{"issue":"9","key":"10.1016\/j.cie.2025.111784_b0115","doi-asserted-by":"crossref","first-page":"3621","DOI":"10.1109\/TITS.2019.2930085","article-title":"Energy-efficient train scheduling and rolling stock circulation planning in a metro line: A linear programming approach","volume":"21","author":"Mo","year":"2019","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"2","key":"10.1016\/j.cie.2025.111784_b0120","doi-asserted-by":"crossref","first-page":"436","DOI":"10.2307\/3212264","article-title":"Queues with time-dependent arrival rates I\u2014the transition through saturation","volume":"5","author":"Newell","year":"1968","journal-title":"Journal of Applied Probability"},{"key":"10.1016\/j.cie.2025.111784_bib302","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping. In","volume":"99","author":"Ng","year":"1999","journal-title":"Icml"},{"key":"10.1016\/j.cie.2025.111784_b0125","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1016\/j.trc.2013.08.016","article-title":"Optimizing urban rail timetable under time-dependent demand and oversaturated conditions","volume":"36","author":"Niu","year":"2013","journal-title":"Transportation Research Part C: Emerging Technologies"},{"issue":"1","key":"10.1016\/j.cie.2025.111784_b0130","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1287\/trsc.6.1.52","article-title":"Control strategies for an idealized public transportation system","volume":"6","author":"Osuna","year":"1972","journal-title":"Transportation science"},{"issue":"1","key":"10.1016\/j.cie.2025.111784_b0135","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1016\/j.ejor.2022.05.039","article-title":"Demand-oriented integration optimization of train timetabling and rolling stock circulation planning with flexible train compositions: A column-generation-based approach","volume":"305","author":"Pan","year":"2023","journal-title":"European Journal of Operational Research"},{"issue":"3","key":"10.1016\/j.cie.2025.111784_b0140","doi-asserted-by":"crossref","first-page":"906","DOI":"10.1016\/j.ejor.2024.02.017","article-title":"New exact Algorithm for the integrated train timetabling and rolling stock circulation planning problem with stochastic demand","volume":"316","author":"Pan","year":"2024","journal-title":"European Journal of Operational Research"},{"key":"10.1016\/j.cie.2025.111784_b0150","series-title":"Reinforcement Learning: An Introduction (2nd edition)","author":"Sutton","year":"2018"},{"key":"10.1016\/j.cie.2025.111784_b0165","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1016\/j.trb.2016.01.004","article-title":"Reinforcement learning approach for train rescheduling on a single-track railway","volume":"86","author":"\u0160emrov","year":"2016","journal-title":"Transportation Research Part B: Methodological"},{"key":"10.1016\/j.cie.2025.111784_b0170","unstructured":"Schulman, J., Moritz, P., Levine, S., Jordan, M., Abbeel, P. (2015). High-dimensional continuous control using generalized advantage estimation. arXiv:1506.02438."},{"key":"10.1016\/j.cie.2025.111784_b0175","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O. (2017). Proximal policy optimization algorithms. arXiv:1707.06347."},{"key":"10.1016\/j.cie.2025.111784_b0185","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2023.109742","article-title":"Integrated train timetabling and rolling stock rescheduling for a disturbed metro system: A hybrid deep reinforcement learning and adaptive large neighborhood search approach","volume":"186","author":"Su","year":"2023","journal-title":"Computers & Industrial Engineering"},{"key":"10.1016\/j.cie.2025.111784_b0190","doi-asserted-by":"crossref","DOI":"10.1016\/j.tre.2024.103900","article-title":"A multi-task deep reinforcement learning approach to real-time railway train rescheduling","volume":"194","author":"Tang","year":"2025","journal-title":"Transportation Research Part E: Logistics and Transportation Review"},{"issue":"7782","key":"10.1016\/j.cie.2025.111784_b0195","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in Starcraft II using multi-agent reinforcement learning","volume":"575","author":"Vinyals","year":"2019","journal-title":"Nature"},{"key":"10.1016\/j.cie.2025.111784_b0200","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.trb.2018.10.006","article-title":"Passenger demand oriented train scheduling and rolling stock circulation planning for an urban rail transit line","volume":"118","author":"Wang","year":"2018","journal-title":"Transportation Research Part B: Methodological"},{"key":"10.1016\/j.cie.2025.111784_b0205","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2021.103209","article-title":"Energy-efficient timetabling and rolling stock circulation planning based on automatic train operation levels for metro lines","volume":"129","author":"Wang","year":"2021","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"10.1016\/j.cie.2025.111784_b0210","unstructured":"Xiong, J., Wang, Q., Yang, Z., Sun, P., Han, L., Zheng, Y., Fu, H. B., Zhang, T., Liu, J., Liu, H. (2018). Parametrized deep q-networks learning: Reinforcement learning with discrete-continuous hybrid action space. arXiv:1810.06394."},{"key":"10.1016\/j.cie.2025.111784_b0215","series-title":"Nature-inspired metaheuristic algorithms","author":"Yang","year":"2010"},{"issue":"10","key":"10.1016\/j.cie.2025.111784_b0220","doi-asserted-by":"crossref","first-page":"856","DOI":"10.1111\/mice.12300","article-title":"Integrated train timetabling and rolling stock scheduling model based on time\u2010dependent demand for urban rail transit","volume":"32","author":"Yue","year":"2017","journal-title":"Computer-Aided Civil and Infrastructure Engineering"},{"key":"10.1016\/j.cie.2025.111784_b0225","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1016\/j.trb.2020.08.005","article-title":"An actor-critic deep reinforcement learning approach for metro train scheduling with rolling stock circulation under stochastic demand","volume":"140","author":"Ying","year":"2020","journal-title":"Transportation Research Part B: Methodological"},{"issue":"7","key":"10.1016\/j.cie.2025.111784_b0230","doi-asserted-by":"crossref","first-page":"6895","DOI":"10.1109\/TITS.2021.3063399","article-title":"Adaptive metro service schedule and train composition with a proximal policy optimization approach based on deep reinforcement learning","volume":"23","author":"Ying","year":"2021","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.cie.2025.111784_b0235","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.trb.2022.05.001","article-title":"Multi-agent deep reinforcement learning for adaptive coordinated metro service operations with flexible train composition","volume":"161","author":"Ying","year":"2022","journal-title":"Transportation Research Part B: Methodological"},{"issue":"3","key":"10.1016\/j.cie.2025.111784_b0240","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1016\/j.ejor.2021.11.019","article-title":"Integrated optimization of train timetable, rolling stock assignment and short-turning strategy for a metro line","volume":"301","author":"Yuan","year":"2022","journal-title":"European Journal of Operational Research"},{"key":"10.1016\/j.cie.2025.111784_b0245","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2023.104237","article-title":"Single-track railway scheduling with a novel gridworld model and scalable deep reinforcement learning","volume":"154","author":"Yang","year":"2023","journal-title":"Transportation research part C: emerging technologies"},{"key":"10.1016\/j.cie.2025.111784_b0250","doi-asserted-by":"crossref","DOI":"10.1016\/j.omega.2023.102968","article-title":"Integrated optimization of train timetable and train unit circulation for a Y-type urban rail transit system with flexible train composition mode","volume":"122","author":"Yang","year":"2024","journal-title":"Omega"},{"key":"10.1016\/j.cie.2025.111784_b0255","doi-asserted-by":"crossref","DOI":"10.1016\/j.trb.2023.102815","article-title":"Integrated optimization of rolling stock allocation and train timetables for urban rail transit networks: A benders decomposition approach","volume":"176","author":"Yin","year":"2023","journal-title":"Transportation Research Part B: Methodological"},{"issue":"7","key":"10.1016\/j.cie.2025.111784_b0260","doi-asserted-by":"crossref","first-page":"6472","DOI":"10.1109\/TITS.2023.3344468","article-title":"Reinforcement Learning for Scalable Train Timetable Rescheduling with Graph Representation","volume":"25","author":"Yue","year":"2024","journal-title":"IEEE Transactions on Intelligent Transportation Systems."},{"key":"10.1016\/j.cie.2025.111784_b0265","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2024.110394","article-title":"Bi-objective optimization of timetable and rolling stock schedule for an urban rail passenger and freight line","volume":"194","author":"Yao","year":"2024","journal-title":"Computers & Industrial Engineering"},{"key":"10.1016\/j.cie.2025.111784_b0270","doi-asserted-by":"crossref","DOI":"10.1016\/j.trb.2024.103067","article-title":"Adaptive rescheduling of rail transit services with short-turnings under disruptions via a multi-agent deep reinforcement learning approach","volume":"188","author":"Ying","year":"2024","journal-title":"Transportation Research Part B: Methodological"},{"key":"10.1016\/j.cie.2025.111784_b0275","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2024.104976","article-title":"An advanced learning environment and a scalable deep reinforcement learning approach for rolling stock circulation on urban rail transit line","volume":"171","author":"Yang","year":"2025","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"10.1016\/j.cie.2025.111784_b0280","article-title":"Optimizing integrated train rescheduling strategies for diverse disruption scenarios using reinforcement learning","volume":"111329","author":"Yin","year":"2025","journal-title":"Computers & Industrial Engineering"},{"key":"10.1016\/j.cie.2025.111784_b0285","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.trb.2019.05.013","article-title":"Rolling stock scheduling with maintenance requirements at the Chinese High-speed Railway","volume":"126","author":"Zhong","year":"2019","journal-title":"Transportation Research Part B: Methodological"},{"key":"10.1016\/j.cie.2025.111784_b0290","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2022.103708","article-title":"Joint optimization of train scheduling and rolling stock circulation planning with passenger flow control on tidal overcrowded metro lines","volume":"140","author":"Zhou","year":"2022","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"10.1016\/j.cie.2025.111784_b0295","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1016\/j.trb.2022.06.007","article-title":"Joint optimization of train timetabling and rolling stock circulation planning: A novel flexible train composition mode","volume":"162","author":"Zhou","year":"2022","journal-title":"Transportation Research Part B: Methodological"},{"key":"10.1016\/j.cie.2025.111784_b0300","doi-asserted-by":"crossref","DOI":"10.1016\/j.tre.2023.103035","article-title":"Integrated optimization of demand-driven timetable, train formation plan and rolling stock circulation with variable running times and dwell times","volume":"171","author":"Zhao","year":"2023","journal-title":"Transportation Research Part E: Logistics and Transportation Review"}],"container-title":["Computers & Industrial Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0360835225009301?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0360835225009301?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T16:44:18Z","timestamp":1771519458000},"score":1,"resource":{"primary":{"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/linkinghub.elsevier.com\/retrieve\/pii\/S0360835225009301"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":53,"alternative-id":["S0360835225009301"],"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.1016\/j.cie.2025.111784","relation":{},"ISSN":["0360-8352"],"issn-type":[{"value":"0360-8352","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A deep reinforcement learning approach for integrated optimization of train scheduling and rolling stock circulation planning","name":"articletitle","label":"Article Title"},{"value":"Computers & Industrial Engineering","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.1016\/j.cie.2025.111784","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"111784"}}