{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T12:07:00Z","timestamp":1776686820738,"version":"3.51.2"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62133011"],"award-info":[{"award-number":["62133011"]}],"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":["62273260"],"award-info":[{"award-number":["62273260"]}],"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":["62373288"],"award-info":[{"award-number":["62373288"]}],"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":["62403365"],"award-info":[{"award-number":["62403365"]}],"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 & Operations Research"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.cor.2026.107499","type":"journal-article","created":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:49:26Z","timestamp":1775231366000},"page":"107499","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Stackelberg game-based production-maintenance collaborative scheduling using meta-enhanced two-stage reinforcement learning"],"prefix":"10.1016","volume":"192","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0027-7226","authenticated-orcid":false,"given":"Jiaxuan","family":"Shi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8934-2127","authenticated-orcid":false,"given":"Juan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9271-3363","authenticated-orcid":false,"given":"Yumin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.cor.2026.107499_b0005","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1007\/s00158-019-02232-8","article-title":"A Stackelberg game theoretic multi-objective synthesis of four-bar mechanisms","volume":"60","author":"Ahmadi","year":"2019","journal-title":"Struct. Multidiscip. Optim."},{"issue":"3","key":"10.1016\/j.cor.2026.107499_b0010","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1049\/iet-stg.2019.0195","article-title":"Energy pricing and demand scheduling in retail market: how microgrids\u2019 integration affects the market","volume":"3","author":"Ahmadi","year":"2020","journal-title":"IET Smart Grid"},{"key":"10.1016\/j.cor.2026.107499_b0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.118711","article-title":"A hybrid multi-objective evolutionary algorithm for solving an adaptive flexible job-shop rescheduling problem with real-time order acceptance and condition-based preventive maintenance","volume":"212","author":"An","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.cor.2026.107499_b0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2022.108135","article-title":"Non-identical parallel machines batch processing problem with release dates, due dates and variable maintenance activity to minimize total tardiness","volume":"168","author":"Beldar","year":"2022","journal-title":"Comput. Ind. Eng."},{"key":"10.1016\/j.cor.2026.107499_b0025","first-page":"221","article-title":"Game theory-based integration of scheduling with flexible and periodic maintenance planning in the permutation flowshop sequencing problem","volume":"18","author":"Benbouzid-Si Tayeb","year":"2018","journal-title":"Oper. Res."},{"issue":"11","key":"10.1016\/j.cor.2026.107499_b0030","doi-asserted-by":"crossref","first-page":"6909","DOI":"10.1109\/TCYB.2024.3413054","article-title":"Learning-based genetic algorithm to schedule an extended flexible job shop","volume":"54","author":"Cao","year":"2024","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.cor.2026.107499_b0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2019.100970","article-title":"A service-oriented multi-player maintenance grouping strategy for complex multi-component system based on game theory","volume":"42","author":"Chang","year":"2019","journal-title":"Adv. Eng. Inf."},{"key":"10.1016\/j.cor.2026.107499_b0040","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/j.jmsy.2019.12.004","article-title":"An approximate nondominated sorting genetic algorithm to integrate optimization of production scheduling and accurate maintenance based on reliability intervals","volume":"54","author":"Chen","year":"2020","journal-title":"J. Manuf. Syst."},{"key":"10.1016\/j.cor.2026.107499_b0045","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1016\/j.jmsy.2025.01.010","article-title":"Multi-workflow dynamic scheduling in product design: a generalizable approach based on meta-reinforcement learning","volume":"79","author":"Chen","year":"2025","journal-title":"J. Manuf. Syst."},{"key":"10.1016\/j.cor.2026.107499_b0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2024.110127","article-title":"Knowledge transfer for adaptive maintenance policy optimization in engineering fleets based on meta-reinforcement learning","volume":"247","author":"Cheng","year":"2024","journal-title":"Reliab. Eng. Syst. Saf."},{"issue":"1","key":"10.1016\/j.cor.2026.107499_b0055","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1109\/TNSE.2023.3283410","article-title":"Toward a virtual edge service provider: actor-Critic learning to incentivize the computation nodes","volume":"11","author":"Cheraghinia","year":"2024","journal-title":"IEEE Trans. Network Sci. Eng."},{"issue":"9","key":"10.1016\/j.cor.2026.107499_b0060","doi-asserted-by":"crossref","first-page":"1619","DOI":"10.3390\/app8091619","article-title":"Research on reliability assessment of mechanical equipment based on the performance-feature model","volume":"8","author":"Dai","year":"2018","journal-title":"Appl. Sci."},{"key":"10.1016\/j.cor.2026.107499_b0065","doi-asserted-by":"crossref","DOI":"10.1109\/TIM.2023.3260283","article-title":"A calibration-based hybrid transfer learning framework for RUL prediction of rolling bearing across different machines","volume":"72","author":"Deng","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"6","key":"10.1016\/j.cor.2026.107499_b0070","doi-asserted-by":"crossref","first-page":"2193","DOI":"10.1109\/TCCN.2024.3400516","article-title":"Balancing performance and cost for two-hop cooperative communications: stackelberg game and distributed multi-agent reinforcement learning","volume":"10","author":"Geng","year":"2024","journal-title":"IEEE Transaction on Cognitive Communications and Networking"},{"key":"10.1016\/j.cor.2026.107499_b0075","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2024.110101","article-title":"Task derivation and decomposition in crowdsourced manufacturing by bilevel coordinated optimization of product family planning and manufacturer load balancing","volume":"190","author":"Gong","year":"2024","journal-title":"Comput. Ind. Eng."},{"issue":"5","key":"10.1016\/j.cor.2026.107499_b0080","doi-asserted-by":"crossref","first-page":"3866","DOI":"10.1109\/TNSM.2025.3579598","article-title":"A bi-level scheme for mixed-motive and energy-efficient task offloading in vehicular edge computing systems","volume":"22","author":"Guo","year":"2025","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"key":"10.1016\/j.cor.2026.107499_b0085","unstructured":"Haarnoja, T., Zhou, A., Hartikainen, K., Tucker, G., Ha, S., Tan, J., Kumar, V., Zhu, H., Gupta, A., Abbeel, P., and Levine, S. (2018). Soft actor-critic algorithms and applications, arXiv preprint arXiv: 1812.05905."},{"issue":"3","key":"10.1016\/j.cor.2026.107499_b0090","doi-asserted-by":"crossref","first-page":"1834","DOI":"10.1109\/TSTE.2024.3380605","article-title":"MADRL-based DSO-customer coordinated bi-level Volt\/VAR optimization method for power distribution networks","volume":"15","author":"Hong","year":"2024","journal-title":"IEEE Transaction on Sustainable Energy"},{"key":"10.1016\/j.cor.2026.107499_b0095","article-title":"Parallel machine scheduling with position-dependent processing times and deteriorating maintenance activities","author":"Hu","year":"2024","journal-title":"J. Glob. Optim."},{"key":"10.1016\/j.cor.2026.107499_b0100","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2023.109708","article-title":"Integrated optimization of production scheduling and maintenance planning with dynamic job arrivals and mold constraints","volume":"186","author":"Hu","year":"2023","journal-title":"Comput. Ind. Eng."},{"issue":"4","key":"10.1016\/j.cor.2026.107499_b0105","doi-asserted-by":"crossref","DOI":"10.1142\/S0217595917500129","article-title":"Joint optimization of production plan and preventive maintenance schedule by Stackelberg game","volume":"34","author":"Hu","year":"2017","journal-title":"Asia-Pacific J. Oper. Res."},{"issue":"14","key":"10.1016\/j.cor.2026.107499_b0110","doi-asserted-by":"crossref","first-page":"4132","DOI":"10.1080\/00207543.2013.835499","article-title":"Availability optimisation for stochastic degrading systems under imperfect preventive maintenance","volume":"52","author":"Khatab","year":"2014","journal-title":"Int. J. Prod. Res."},{"issue":"11","key":"10.1016\/j.cor.2026.107499_b0115","doi-asserted-by":"crossref","first-page":"6836","DOI":"10.1109\/TSMC.2023.3287655","article-title":"Dynamic job-shop scheduling problems using graph neural network and deep reinforcement learning","volume":"53","author":"Liu","year":"2023","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"key":"10.1016\/j.cor.2026.107499_b0120","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2021.107489","article-title":"Dynamic multi-objective scheduling for flexible job shop by deep reinforcement learning","volume":"159","author":"Luo","year":"2021","journal-title":"Comput. Ind. Eng."},{"issue":"7","key":"10.1016\/j.cor.2026.107499_b0125","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1080\/00949655.2021.1993224","article-title":"Time between events monitoring for imperfect maintained systems with application to a robotic system","volume":"92","author":"Maged","year":"2022","journal-title":"J. Stat. Comput. Simul."},{"key":"10.1016\/j.cor.2026.107499_b0130","unstructured":"Nichol, A., Achiam, J., and Schulman, J. (2018). On first-order meta-learning algorithms, arXiv preprint arXiv:1803.02999."},{"key":"10.1016\/j.cor.2026.107499_b0135","doi-asserted-by":"crossref","DOI":"10.1016\/j.jnca.2023.103600","article-title":"Stackelberg game-based dynamic resource trading for network slicing in 5G network","volume":"214","author":"Ou","year":"2023","journal-title":"J. Netw. Comput. Appl."},{"key":"10.1016\/j.cor.2026.107499_b0140","doi-asserted-by":"crossref","DOI":"10.1016\/j.cor.2023.106365","article-title":"A multi-agent system for integrated scheduling and maintenance planning of the flexible job shop","volume":"159","author":"Pal","year":"2023","journal-title":"Comput. Oper. Res."},{"key":"10.1016\/j.cor.2026.107499_b0145","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2020.106369","article-title":"Permutation flowshop scheduling with periodic maintenance and makespan objective","volume":"143","author":"Perez-Gonzalez","year":"2020","journal-title":"Comput. Ind. Eng."},{"key":"10.1016\/j.cor.2026.107499_b0150","unstructured":"Schaul, T. (2015). Prioritized experience replay, arXiv preprint arXiv:1511.05952."},{"key":"10.1016\/j.cor.2026.107499_b0155","doi-asserted-by":"crossref","first-page":"3171","DOI":"10.1007\/s12652-018-1032-8","article-title":"A parallel-machine scheduling problem with periodic maintenance under uncertainty","volume":"10","author":"Shen","year":"2019","journal-title":"J. Ambient Intell. Hum. Comput."},{"key":"10.1016\/j.cor.2026.107499_b0160","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.103195","article-title":"Production-logistics collaborative scheduling in dynamic flexible job shops using nested-hierarchical deep reinforcement learning","volume":"65","author":"Shi","year":"2025","journal-title":"Adv. Eng. Inf."},{"issue":"5","key":"10.1016\/j.cor.2026.107499_b0165","doi-asserted-by":"crossref","first-page":"3830","DOI":"10.1109\/TMC.2023.3281203","article-title":"Competitive pricing for resource trading in sliced mobile networks: a multi-agent reinforcement learning approach","volume":"23","author":"Sun","year":"2024","journal-title":"IEEE Trans. Mob. Comput."},{"key":"10.1016\/j.cor.2026.107499_b0170","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2022.124806","article-title":"High robustness energy management strategy of hybrid electric vehicle based on improved soft actor-critic deep reinforcement learning","volume":"258","author":"Sun","year":"2022","journal-title":"Energy"},{"key":"10.1016\/j.cor.2026.107499_b0175","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2021.101339","article-title":"Integrated scheduling and flexible maintenance in deteriorating multi-state single machine system using a reinforcement learning approach","volume":"49","author":"Wang","year":"2021","journal-title":"Adv. Eng. Inf."},{"key":"10.1016\/j.cor.2026.107499_b0180","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1016\/j.ejor.2018.05.050","article-title":"A branch-and-price algorithm for scheduling of deteriorating jobs and flexible periodic maintenance on a single machine","volume":"271","author":"Wang","year":"2018","journal-title":"Eur. J. Oper. Res."},{"key":"10.1016\/j.cor.2026.107499_b0185","series-title":"In Proceedings of 2020 International Conference on Smart Grids and Energy Systems","first-page":"60","article-title":"Energy co-pricing in an integrated energy system for promoting electric energy substitution","author":"Wang","year":"2020"},{"key":"10.1016\/j.cor.2026.107499_b0190","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijpe.2024.109163","article-title":"Joint optimization of flexible job shop scheduling and preventive maintenance under high-frequency production switching","volume":"269","author":"Wang","year":"2024","journal-title":"Int. J. Prod. Econ."},{"issue":"3","key":"10.1016\/j.cor.2026.107499_b0195","doi-asserted-by":"crossref","first-page":"150","DOI":"10.3390\/systems11030150","article-title":"Two due-date assignment scheduling with location-dependent weights and a deteriorating maintenance activity","volume":"11","author":"Wu","year":"2023","journal-title":"Systems"},{"issue":"6","key":"10.1016\/j.cor.2026.107499_b0200","doi-asserted-by":"crossref","first-page":"4938","DOI":"10.1109\/TAES.2022.3211247","article-title":"Double-layer Q-learning-based joint decision-making of dual resource-constrained aircraft assembly scheduling and flexible preventive maintenance","volume":"58","author":"Yan","year":"2022","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"10.1016\/j.cor.2026.107499_b0205","doi-asserted-by":"crossref","DOI":"10.1016\/j.cor.2022.105823","article-title":"Digital twin-enabled dynamic scheduling with preventive maintenance using a double-layer Q-learning algorithm","volume":"144","author":"Yan","year":"2022","journal-title":"Comput. Oper. Res."},{"key":"10.1016\/j.cor.2026.107499_b0210","doi-asserted-by":"crossref","DOI":"10.1016\/j.cor.2025.107149","article-title":"Deep reinforcement learning based proximal policy optimization algorithm for dynamic job shop scheduling","volume":"183","author":"Yuan","year":"2025","journal-title":"Comput. Oper. Res."},{"key":"10.1016\/j.cor.2026.107499_b0215","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1016\/j.jmsy.2025.03.025","article-title":"Self-optimization in distributed manufacturing systems using modular state-based Stackelberg games","volume":"80","author":"Yuwono","year":"2025","journal-title":"J. Manuf. Syst."},{"issue":"1","key":"10.1016\/j.cor.2026.107499_b0220","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1109\/TCYB.2025.3610707","article-title":"Integrating deep model-based learning with modular state-based Stackelberg games for self-optimizing distributed production systems","volume":"56","author":"Yuwono","year":"2026","journal-title":"IEEE Trans. Cybern."},{"issue":"11","key":"10.1016\/j.cor.2026.107499_b0225","doi-asserted-by":"crossref","first-page":"8112","DOI":"10.1109\/TSMC.2025.3602958","article-title":"Distributed stackelberg strategies in state-based potential games for autonomous decentralized learning manufacturing systems","volume":"55","author":"Yuwono","year":"2025","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"issue":"4","key":"10.1016\/j.cor.2026.107499_b0230","doi-asserted-by":"crossref","first-page":"2681","DOI":"10.1109\/TSMC.2025.3525776","article-title":"A Stackelberg game framework for double-incentive consensus mechanism with cost budget in group decision making","volume":"55","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"issue":"12","key":"10.1016\/j.cor.2026.107499_b0235","doi-asserted-by":"crossref","first-page":"8999","DOI":"10.1109\/TII.2022.3178410","article-title":"Distributed real-time scheduling in cloud manufacturing by deep reinforcement learning","volume":"18","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Ind. Inf."},{"key":"10.1016\/j.cor.2026.107499_b0240","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.jmsy.2023.08.011","article-title":"Counterfactual-attention multi-agent reinforcement learning for joint condition-based maintenance and production scheduling","volume":"71","author":"Zhang","year":"2023","journal-title":"J. Manuf. Syst."},{"issue":"7","key":"10.1016\/j.cor.2026.107499_b0245","doi-asserted-by":"crossref","first-page":"4079","DOI":"10.1109\/TCYB.2021.3135539","article-title":"The hot strip mill scheduling problem with uncertainty: robust optimization models and solution approaches","volume":"53","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.cor.2026.107499_b0250","doi-asserted-by":"crossref","DOI":"10.1016\/j.physa.2024.130289","article-title":"Coupled vehicle-signal control based on Stackelberg game enabled multi-agent reinforcement learning in mixed traffic environment","volume":"658","author":"Zhang","year":"2025","journal-title":"Phys. A"},{"key":"10.1016\/j.cor.2026.107499_b0255","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1016\/j.jclepro.2017.08.068","article-title":"Game theory based real-time multi-objective flexible job shop scheduling considering environmental impact","volume":"167","author":"Zhang","year":"2017","journal-title":"J. Clean. Prod."},{"key":"10.1016\/j.cor.2026.107499_b0260","doi-asserted-by":"crossref","DOI":"10.1016\/j.cor.2025.107267","article-title":"A Q-learning-based multi-objective hyper-heuristic algorithm for energy-efficient integrated distributed hybrid flow-shop scheduling with preventive maintenance","volume":"185","author":"Zhang","year":"2026","journal-title":"Comput. Oper. Res."},{"key":"10.1016\/j.cor.2026.107499_b0265","series-title":"In 2016 IEEE Power and Energy Society General Meeting (PESGM)","first-page":"1","article-title":"Reliability assessment of distribution network considering preventive maintenance","author":"Zhao","year":"2016"},{"issue":"3","key":"10.1016\/j.cor.2026.107499_b0270","doi-asserted-by":"crossref","first-page":"2422","DOI":"10.1109\/TITS.2021.3114295","article-title":"A deep reinforcement learning-based resource management game in vehicular edge computing","volume":"23","author":"Zhu","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."}],"container-title":["Computers & Operations Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0305054826001176?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0305054826001176?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T11:22:52Z","timestamp":1776684172000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0305054826001176"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":54,"alternative-id":["S0305054826001176"],"URL":"https:\/\/doi.org\/10.1016\/j.cor.2026.107499","relation":{},"ISSN":["0305-0548"],"issn-type":[{"value":"0305-0548","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Stackelberg game-based production-maintenance collaborative scheduling using meta-enhanced two-stage reinforcement learning","name":"articletitle","label":"Article Title"},{"value":"Computers & Operations Research","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cor.2026.107499","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":"107499"}}