{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T02:00:07Z","timestamp":1781920807361,"version":"3.54.5"},"reference-count":71,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T00:00:00Z","timestamp":1770422400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Foundation for Science and Technology","doi-asserted-by":"publisher","award":["2022.14822"],"award-info":[{"award-number":["2022.14822"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Foundation for Science and Technology","doi-asserted-by":"publisher","award":["PTDC\/EME-SIS\/6019\/2020"],"award-info":[{"award-number":["PTDC\/EME-SIS\/6019\/2020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Foundation for Science and Technology","doi-asserted-by":"publisher","award":["UID\/00285\/2025"],"award-info":[{"award-number":["UID\/00285\/2025"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Foundation for Science and Technology","doi-asserted-by":"publisher","award":["LA\/P\/0112\/2020"],"award-info":[{"award-number":["LA\/P\/0112\/2020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["C645808870-00000067"],"award-info":[{"award-number":["C645808870-00000067"]}],"id":[{"id":"10.13039\/501100000780","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":[[2026,6]]},"DOI":"10.1016\/j.cor.2026.107428","type":"journal-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T16:09:06Z","timestamp":1770826146000},"page":"107428","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["Enhancing multi-agent deep reinforcement learning for flexible job-shop scheduling through constraint programming"],"prefix":"10.1016","volume":"190","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0563-8156","authenticated-orcid":false,"given":"Alexandre","family":"Jesus","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4949-4791","authenticated-orcid":false,"given":"Arthur","family":"Corr\u00eaa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miguel","family":"Vieira","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Catarina","family":"Marques","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7693-9570","authenticated-orcid":false,"given":"Crist\u00f3v\u00e3o","family":"Silva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7813-4514","authenticated-orcid":false,"given":"Samuel","family":"Moniz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cor.2026.107428_b0005","doi-asserted-by":"crossref","unstructured":"Belkhale, S., Cui, Y., & Sadigh, D. (2023). Data Quality in Imitation Learning.","DOI":"10.52202\/075280-3524"},{"issue":"2","key":"10.1016\/j.cor.2026.107428_b0010","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1016\/j.ejor.2020.07.063","article-title":"Machine learning for combinatorial optimization: A methodological tour d\u2019horizon","volume":"290","author":"Bengio","year":"2021","journal-title":"Eur. J. Operat. Res."},{"key":"10.1016\/j.cor.2026.107428_b0015","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/BF02023073","article-title":"Routing and scheduling in a flexible job shop by tabu search","volume":"41","author":"Brandimarte","year":"1993","journal-title":"Ann. Oper. Res."},{"key":"10.1016\/j.cor.2026.107428_b0020","series-title":"Proceedings of the 24th International Conference on Artificial Intelligence","first-page":"3352","article-title":"Reinforcement learning from demonstration through shaping","author":"Brys","year":"2015"},{"key":"10.1016\/j.cor.2026.107428_b0025","unstructured":"Cappart, Q., Moisan, T., Rousseau, L.-M., Pr\u00e9mont-Schwarz, I., & Cire, A. (2020). Combining reinforcement learning and constraint programming for combinatorial optimization. http:\/\/arxiv.org\/abs\/2006.01610."},{"key":"10.1016\/j.cor.2026.107428_b0030","unstructured":"Chen, W., Khir, R., & Van Hentenryck, P. (2023). Two-Stage Learning For the Flexible Job Shop Scheduling Problem. http:\/\/arxiv.org\/abs\/2301.09703."},{"key":"10.1016\/j.cor.2026.107428_b0035","unstructured":"Dai, H., Khalil, E. B., Zhang, Y., Dilkina, B., & Song, L. (2018). Learning Combinatorial Optimization Algorithms over Graphs. http:\/\/arxiv.org\/abs\/1704.01665."},{"key":"10.1016\/j.cor.2026.107428_b0040","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1023\/A:1018930406487","article-title":"An integrated approach for modeling and solving the general multiprocessor job-shop scheduling problem using tabu search","volume":"70","author":"Dauz\u00e8re-P\u00e9r\u00e8s","year":"1997","journal-title":"Ann. Oper. Res."},{"key":"10.1016\/j.cor.2026.107428_b0045","first-page":"1","article-title":"Plan-based reward shaping for multi-agent reinforcement learning","volume":"00","author":"Devlin","year":"2004","journal-title":"Knowl. Eng. Rev."},{"key":"10.1016\/j.cor.2026.107428_b0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109488","article-title":"Diverse policy generation for the flexible job-shop scheduling problem via deep reinforcement learning with a novel graph representation","volume":"139","author":"Echeverria","year":"2025","journal-title":"Eng. Appl. Artif. Intel."},{"key":"10.1016\/j.cor.2026.107428_b0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125895","article-title":"Leveraging constraint programming in a deep learning approach for dynamically solving the flexible job-shop scheduling problem","volume":"265","author":"Echeverria","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.cor.2026.107428_b0060","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2025.113736","article-title":"Offline reinforcement learning for job-shop scheduling problems","volume":"184","author":"Echeverria","year":"2025","journal-title":"Appl. Soft Comput."},{"issue":"3","key":"10.1016\/j.cor.2026.107428_b0065","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1007\/s10845-007-0026-8","article-title":"Mathematical modeling and heuristic approaches to flexible job shop scheduling problems","volume":"18","author":"Fattahi","year":"2007","journal-title":"J. Intell. Manuf."},{"key":"10.1016\/j.cor.2026.107428_b0070","unstructured":"Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., & Whiteson, S. (2024). Counterfactual Multi-Agent Policy Gradients. http:\/\/arxiv.org\/abs\/1705.08926."},{"key":"10.1016\/j.cor.2026.107428_b0075","series-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems","first-page":"2145","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"Foerster","year":"2016"},{"key":"10.1016\/j.cor.2026.107428_b0080","unstructured":"Foerster, J. N., de Witt, C. A. S., Farquhar, G., Torr, P. H. S., Boehmer, W., & Whiteson, S. (2018). Multi-agent common knowledge reinforcement learning. CoRR, abs\/1810.11702. http:\/\/arxiv.org\/abs\/1810.11702."},{"key":"10.1016\/j.cor.2026.107428_b0085","unstructured":"Foster, D. J., Block, A., & Misra, D. (2024). Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning. http:\/\/arxiv.org\/abs\/2407.15007."},{"issue":"4","key":"10.1016\/j.cor.2026.107428_b0090","doi-asserted-by":"crossref","first-page":"904","DOI":"10.1109\/JAS.2019.1911540","article-title":"A review on swarm intelligence and evolutionary algorithms for solving flexible job shop scheduling problems","volume":"6","author":"Gao","year":"2019","journal-title":"IEEE\/CAA J. Automat. Sin."},{"issue":"C","key":"10.1016\/j.cor.2026.107428_b0095","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1016\/j.cie.2016.11.001","article-title":"Flexible job shop scheduling problem with parallel batch processing machines","volume":"102","author":"Ham","year":"2016","journal-title":"Comput. Ind. Eng."},{"key":"10.1016\/j.cor.2026.107428_b0100","series-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence","article-title":"Deep Q-learning from demonstrations","author":"Hester","year":"2018"},{"key":"10.1016\/j.cor.2026.107428_b0105","unstructured":"Ho, J., & Ermon, S. (2016). Generative Adversarial Imitation Learning. http:\/\/arxiv.org\/abs\/1606.03476."},{"key":"10.1016\/j.cor.2026.107428_b0110","doi-asserted-by":"crossref","first-page":"14703","DOI":"10.1109\/ACCESS.2024.3357969","article-title":"Residual scheduling: a new reinforcement learning approach to solving job shop scheduling problem","volume":"12","author":"Ho","year":"2024","journal-title":"IEEE Access"},{"issue":"4","key":"10.1016\/j.cor.2026.107428_b0115","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1007\/BF01719451","article-title":"Tabu search for the job-shop scheduling problem with multi-purpose machines","volume":"15","author":"Hurink","year":"1994","journal-title":"Operat.-Res.-Spektrum"},{"issue":"4","key":"10.1016\/j.cor.2026.107428_b0120","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1007\/s10951-017-0534-0","article-title":"Discovering dispatching rules from data using imitation learning: a case study for the job-shop problem","volume":"21","author":"Ingimundardottir","year":"2018","journal-title":"J. Sched."},{"key":"10.1016\/j.cor.2026.107428_b0125","doi-asserted-by":"crossref","unstructured":"Jang, J., Klabjan, D., Liu, H., Patel, N. S., Li, X., Ananthanarayanan, B., Dauod, H., & Juang, T.-H. (2024). Scalable Multi-agent Reinforcement Learning for Factory-wide Dynamic Scheduling. http:\/\/arxiv.org\/abs\/2409.13571.","DOI":"10.1016\/j.engappai.2025.112168"},{"issue":"1","key":"10.1016\/j.cor.2026.107428_b0130","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1007\/s10845-022-02037-5","article-title":"Multi-agent reinforcement learning based on graph convolutional network for flexible job shop scheduling","volume":"35","author":"Jing","year":"2024","journal-title":"J. Intell. Manuf."},{"key":"10.1016\/j.cor.2026.107428_b0135","unstructured":"Kang, B., Jie, Z., & Feng, J. (2018). Policy Optimization with Demonstrations."},{"issue":"7","key":"10.1016\/j.cor.2026.107428_b0140","doi-asserted-by":"crossref","first-page":"2322","DOI":"10.1111\/poms.13977","article-title":"On the multiresource flexible job-shop scheduling problem with arbitrary precedence graphs","volume":"32","author":"Kasapidis","year":"2023","journal-title":"Prod. Oper. Manag."},{"issue":"3","key":"10.1016\/j.cor.2026.107428_b0145","doi-asserted-by":"crossref","first-page":"905","DOI":"10.1007\/s10845-021-01847-3","article-title":"Reinforcement learning applications to machine scheduling problems: a comprehensive literature review","volume":"34","author":"Kayhan","year":"2023","journal-title":"J. Intell. Manuf."},{"key":"10.1016\/j.cor.2026.107428_b0150","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2025.110856","article-title":"Deep reinforcement learning for machine scheduling: Methodology, the state-of-the-art, and future directions","volume":"200","author":"Khadivi","year":"2025","journal-title":"Comput. Ind. Eng."},{"key":"10.1016\/j.cor.2026.107428_b0155","unstructured":"Kool, W., van Hoof, H., & Welling, M. (2019). Attention, Learn to Solve Routing Problems! http:\/\/arxiv.org\/abs\/1803.08475."},{"key":"10.1016\/j.cor.2026.107428_b0160","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.neucom.2016.01.031","article-title":"Multi-agent reinforcement learning as a rehearsal for decentralized planning","volume":"190","author":"Kraemer","year":"2016","journal-title":"Neurocomputing"},{"issue":"2","key":"10.1016\/j.cor.2026.107428_b0165","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1007\/s10601-018-9281-x","article-title":"IBM ILOG CP optimizer for scheduling","volume":"23","author":"Laborie","year":"2018","journal-title":"Constraints"},{"key":"10.1016\/j.cor.2026.107428_b0170","doi-asserted-by":"crossref","first-page":"8593","DOI":"10.1109\/TASE.2024.3486919","article-title":"Graph-based Imitation Learning for Real-Time Job Shop Dispatcher","volume":"22","author":"Lee","year":"2025","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.cor.2026.107428_b0175","unstructured":"Li, L., Liang, S., Zhu, Z., Ding, C., Zha, H., & Wu, B. (2023). Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learning. http:\/\/arxiv.org\/abs\/2210.17178."},{"key":"10.1016\/j.cor.2026.107428_b0180","series-title":"Proceedings of the 42nd International Conference on Machine Learning","first-page":"37456","article-title":"BOPO: neural combinatorial optimization via best-anchored and objective-guided preference optimization","author":"Liao","year":"2025"},{"issue":"6","key":"10.1016\/j.cor.2026.107428_b0185","doi-asserted-by":"crossref","first-page":"8662","DOI":"10.1109\/TII.2024.3371489","article-title":"Dynamic job-shop scheduling via graph attention networks and deep reinforcement learning","volume":"20","author":"Liu","year":"2024","journal-title":"IEEE Trans. Ind. Inf."},{"key":"10.1016\/j.cor.2026.107428_b0190","doi-asserted-by":"crossref","DOI":"10.1016\/j.cor.2023.106294","article-title":"A deep multi-agent reinforcement learning approach to solve dynamic job shop scheduling problem","volume":"159","author":"Liu","year":"2023","journal-title":"Comput. Oper. Res."},{"key":"10.1016\/j.cor.2026.107428_bib348","series-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS'17)","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"Lowe","year":"2017"},{"key":"10.1016\/j.cor.2026.107428_b0195","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2020.106347","article-title":"Mixed-integer linear programming and constraint programming formulations for solving distributed flexible job shop scheduling problem","volume":"142","author":"Meng","year":"2020","journal-title":"Comput. Ind. Eng."},{"issue":"4","key":"10.1016\/j.cor.2026.107428_b0200","doi-asserted-by":"crossref","first-page":"817","DOI":"10.1287\/ijoc.2023.1287","article-title":"Mixed-integer programming vs. constraint programming for shop scheduling problems: new results and outlook","volume":"35","author":"Naderi","year":"2023","journal-title":"INFORMS J. Comput."},{"key":"10.1016\/j.cor.2026.107428_b0205","series-title":"Proceedings of the Sixteenth International Conference on Machine Learning","first-page":"278","article-title":"Policy invariance under reward transformations: theory and application to reward shaping","author":"Ng","year":"1999"},{"issue":"1\u20132","key":"10.1016\/j.cor.2026.107428_b0210","first-page":"1","article-title":"An algorithmic perspective on imitation learning","volume":"7","author":"Osa","year":"2018","journal-title":"Foundat. Trends\u00ae Robotics"},{"issue":"13","key":"10.1016\/j.cor.2026.107428_b0215","doi-asserted-by":"crossref","first-page":"4316","DOI":"10.1080\/00207543.2021.1973138","article-title":"Deep reinforcement learning in production systems: a systematic literature review","volume":"60","author":"Panzer","year":"2022","journal-title":"Int. J. Prod. Res."},{"key":"10.1016\/j.cor.2026.107428_b0220","unstructured":"Park, J., Bakhtiyar, S., & Park, J. (2021). ScheduleNet: Learn to solve multi-agent scheduling problems with reinforcement learning."},{"issue":"11","key":"10.1016\/j.cor.2026.107428_b0225","doi-asserted-by":"crossref","first-page":"3360","DOI":"10.1080\/00207543.2020.1870013","article-title":"Learning to schedule job-shop problems: representation and policy learning using graph neural network and reinforcement learning","volume":"59","author":"Park","year":"2021","journal-title":"Int. J. Prod. Res."},{"key":"10.1016\/j.cor.2026.107428_b0230","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., K\u00f6pf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., \u2026 Chintala, S. (2019). PyTorch: An Imperative Style, High-Performance Deep Learning Library. ArXiv, abs\/1912.01703. https:\/\/api.semanticscholar.org\/CorpusID:202786778."},{"key":"10.1016\/j.cor.2026.107428_b0235","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.procir.2022.09.039","article-title":"Using multi-agent deep reinforcement learning for flexible job shop scheduling problems","volume":"112","author":"Popper","year":"2022","journal-title":"Procedia CIRP"},{"key":"10.1016\/j.cor.2026.107428_b0240","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1016\/j.jmsy.2023.03.003","article-title":"Dynamic production scheduling towards self-organizing mass personalization: a multi-agent dueling deep reinforcement learning approach","volume":"68","author":"Qin","year":"2023","journal-title":"J. Manuf. Syst."},{"key":"10.1016\/j.cor.2026.107428_b0245","unstructured":"Reddy, S., Dragan, A. D., & Levine, S. (2019). SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards. http:\/\/arxiv.org\/abs\/1905.11108."},{"key":"10.1016\/j.cor.2026.107428_b0250","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.131654","article-title":"Algorithmically-designed reward shaping for multiagent reinforcement learning in navigation","volume":"658","author":"Saeed","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.cor.2026.107428_b0255","unstructured":"Schulman, J., Moritz, P., Levine, S., Jordan, M., & Abbeel, P. (2018). High-Dimensional Continuous Control Using Generalized Advantage Estimation."},{"key":"10.1016\/j.cor.2026.107428_b0260","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017). Proximal Policy Optimization Algorithms."},{"issue":"2","key":"10.1016\/j.cor.2026.107428_b0265","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1016\/j.ejor.2017.08.021","article-title":"Solving the flexible job shop scheduling problem with sequence-dependent setup times","volume":"265","author":"Shen","year":"2018","journal-title":"Eur. J. Oper. Res."},{"key":"10.1016\/j.cor.2026.107428_b0270","doi-asserted-by":"crossref","unstructured":"Smit, I. G., Zhou, J., Reijnen, R., Wu, Y., Chen, J., Zhang, C., Bukhsh, Z., Zhang, Y., & Nuijten, W. (2025). Graph neural networks for job shop scheduling problems: A survey. In Computers and Operations Research (Vol. 176). Elsevier Ltd. https:\/\/doi.org\/10.1016\/j.cor.2024.106914.","DOI":"10.1016\/j.cor.2024.106914"},{"issue":"2","key":"10.1016\/j.cor.2026.107428_b0275","doi-asserted-by":"crossref","first-page":"1600","DOI":"10.1109\/TII.2022.3189725","article-title":"Flexible Job-Shop Scheduling via Graph Neural Network and Deep Reinforcement Learning","volume":"19","author":"Song","year":"2023","journal-title":"IEEE Trans. Ind. Inf."},{"key":"10.1016\/j.cor.2026.107428_b0280","doi-asserted-by":"crossref","unstructured":"Tassel, P., Gebser, M., & Schekotihin, K. (2023). An End-to-End Reinforcement Learning Approach for Job-Shop Scheduling Problems Based on Constraint Programming. www.aaai.org.","DOI":"10.1609\/icaps.v33i1.27243"},{"key":"10.1016\/j.cor.2026.107428_b0285","series-title":"Operational Research","first-page":"171","article-title":"Towards an integrated decision-support framework for the new generation of manufacturing systems","author":"Vieira","year":"2021"},{"key":"10.1016\/j.cor.2026.107428_b0290","unstructured":"Vinyals, O., Fortunato, M., & Jaitly, N. (2015). Pointer Networks. http:\/\/arxiv.org\/abs\/1506.03134."},{"key":"10.1016\/j.cor.2026.107428_b0295","doi-asserted-by":"crossref","DOI":"10.1016\/j.comnet.2021.107969","article-title":"Dynamic job-shop scheduling in smart manufacturing using deep reinforcement learning","volume":"190","author":"Wang","year":"2021","journal-title":"Comput. Netw."},{"key":"10.1016\/j.cor.2026.107428_b0300","doi-asserted-by":"crossref","unstructured":"Wang, R., Wang, G., Sun, J., Deng, F., & Chen, J. (2023). Flexible Job Shop Scheduling via Dual Attention Network Based Reinforcement Learning.","DOI":"10.1109\/TNNLS.2023.3306421"},{"issue":"3","key":"10.1016\/j.cor.2026.107428_b0305","doi-asserted-by":"crossref","first-page":"3091","DOI":"10.1109\/TNNLS.2023.3306421","article-title":"Flexible Job Shop Scheduling via dual attention Network-based Reinforcement Learning","volume":"35","author":"Wang","year":"2024","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.cor.2026.107428_b0310","doi-asserted-by":"crossref","unstructured":"Waubert de Puiseau, C., Meyes, R., & Meisen, T. (2022). On reliability of reinforcement learning based production scheduling systems: a comparative survey. In Journal of Intelligent Manufacturing (Vol. 33, Issue 4, pp. 911\u2013927). Springer. https:\/\/doi.org\/10.1007\/s10845-022-01915-2.","DOI":"10.1007\/s10845-022-01915-2"},{"issue":"3","key":"10.1016\/j.cor.2026.107428_b0315","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1080\/00401706.1962.10490022","article-title":"Note on a method for calculating corrected sums of squares and products","volume":"4","author":"Welford","year":"1962","journal-title":"Technometrics"},{"key":"10.1016\/j.cor.2026.107428_b0320","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A Comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2019","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.cor.2026.107428_b0325","doi-asserted-by":"crossref","DOI":"10.1016\/j.cor.2022.105731","article-title":"A survey of job shop scheduling problem: the types and models","volume":"142","author":"Xiong","year":"2022","journal-title":"Comput. Oper. Res."},{"key":"10.1016\/j.cor.2026.107428_b0330","series-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","article-title":"Hybrid policy optimization from Imperfect demonstrations","author":"Yang","year":"2023"},{"key":"10.1016\/j.cor.2026.107428_b0335","unstructured":"Yu, C., Velu, A., Vinitsky, E., Gao, J., Wang, Y., Bayen, A., & Wu, Y. (2022). The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games."},{"key":"10.1016\/j.cor.2026.107428_b0340","series-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","article-title":"Learning to dispatch for job shop scheduling via deep reinforcement learning","author":"Zhang","year":"2020"},{"key":"10.1016\/j.cor.2026.107428_bib347","article-title":"Multi-agent reinforcement learning: A selective overview of theories and algorithms","volume":"325","author":"Zhang","year":"2021"},{"key":"10.1016\/j.cor.2026.107428_b0345","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.110083","article-title":"DeepMAG: deep reinforcement learning with multi-agent graphs for flexible job shop scheduling","volume":"259","author":"Zhang","year":"2023","journal-title":"Knowl.-Based Syst."}],"container-title":["Computers & Operations Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0305054826000468?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0305054826000468?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:59:37Z","timestamp":1776182377000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0305054826000468"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":71,"alternative-id":["S0305054826000468"],"URL":"https:\/\/doi.org\/10.1016\/j.cor.2026.107428","relation":{},"ISSN":["0305-0548"],"issn-type":[{"value":"0305-0548","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Enhancing multi-agent deep reinforcement learning for flexible job-shop scheduling through constraint programming","name":"articletitle","label":"Article Title"},{"value":"Computers & Operations Research","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cor.2026.107428","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"107428"}}