{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T07:06:47Z","timestamp":1779520007636,"version":"3.53.1"},"reference-count":115,"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"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers & Industrial Engineering"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.cie.2026.112048","type":"journal-article","created":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T15:06:43Z","timestamp":1777129603000},"page":"112048","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A novel deep reinforcement learning method for solving resource-constrained multi-project scheduling problem: twin delayed deep deterministic policy gradient"],"prefix":"10.1016","volume":"217","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1605-8381","authenticated-orcid":false,"given":"Sajad","family":"Soltan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0953-6381","authenticated-orcid":false,"given":"Maryam","family":"Ashrafi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2649-3440","authenticated-orcid":false,"given":"Ehsan","family":"Nazerfard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.cie.2026.112048_b0005","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1007\/s10732-024-09540-3","article-title":"Hybridizing constraint programming and meta-heuristics for multi-mode resource-constrained multiple projects scheduling Problem","volume":"31","author":"Ahmeti","year":"2025","journal-title":"Journal of Heuristics"},{"key":"10.1016\/j.cie.2026.112048_b0010","series-title":"In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining","first-page":"2623","article-title":"Optuna: A next-generation hyperparameter optimization framework","author":"Akiba","year":"2019"},{"key":"10.1016\/j.cie.2026.112048_b0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.cor.2019.104782","article-title":"Strong bounds for resource constrained project scheduling: Preprocessing and cutting planes","volume":"113","author":"Araujo","year":"2020","journal-title":"Computers & Operations Research"},{"key":"10.1016\/j.cie.2026.112048_b0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2021.107427","article-title":"Resource constrained project scheduling and material ordering problem with discounted cash flows","volume":"158","author":"Asadujjaman","year":"2021","journal-title":"Computers & Industrial Engineering"},{"key":"10.1016\/j.cie.2026.112048_b0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2024.110380","article-title":"Supply chain integrated resource-constrained multi-project scheduling problem","volume":"194","author":"Asadujjaman","year":"2024","journal-title":"Computers & Industrial Engineering"},{"key":"10.1016\/j.cie.2026.112048_b0030","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1016\/j.comcom.2022.09.002","article-title":"Deep reinforcement learning based trajectory optimization for magnetometer-mounted UAV to landmine detection","volume":"195","author":"Barnawi","year":"2022","journal-title":"Computer Communications"},{"issue":"1","key":"10.1016\/j.cie.2026.112048_b0035","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.ejor.2022.11.009","article-title":"Multi-project scheduling: A benchmark analysis of metaheuristic algorithms on various optimisation criteria and due dates","volume":"308","author":"Bredael","year":"2023","journal-title":"European Journal of Operational Research"},{"issue":"1","key":"10.1016\/j.cie.2026.112048_b0040","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.ejor.2023.11.009","article-title":"A genetic algorithm with resource buffers for the resource-constrained multi-project scheduling problem","volume":"315","author":"Bredael","year":"2024","journal-title":"European Journal of Operational Research"},{"key":"10.1016\/j.cie.2026.112048_b0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.rcim.2023.102628","article-title":"Deep reinforcement learning for solving resource constrained project scheduling problems with resource disruptions","volume":"85","author":"Cai","year":"2024","journal-title":"Robotics and Computer-Integrated Manufacturing"},{"issue":"6","key":"10.1016\/j.cie.2026.112048_b0050","doi-asserted-by":"crossref","first-page":"7055","DOI":"10.1007\/s40747-023-01087-3","article-title":"A problem-specific parallel pareto local search for the reactive decision support of a special RCPSP extension","volume":"9","author":"Cai","year":"2023","journal-title":"Complex & Intelligent Systems"},{"issue":"5","key":"10.1016\/j.cie.2026.112048_b0055","doi-asserted-by":"crossref","first-page":"4513","DOI":"10.1109\/TSG.2020.2986333","article-title":"Deep reinforcement learning-based energy storage arbitrage with accurate lithium-ion battery degradation model","volume":"11","author":"Cao","year":"2020","journal-title":"IEEE Transactions on Smart Grid"},{"key":"10.1016\/j.cie.2026.112048_b0060","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128881","article-title":"A genetic programming hyper-heuristic with whale optimization algorithm for the dynamic resource-constrained multi-project scheduling problems","volume":"295","author":"Chao","year":"2026","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.cie.2026.112048_b0065","doi-asserted-by":"crossref","unstructured":"Chau, T., Nguyen, M. T., Ngo, D. V., Nguyen, A. D. T., & Do, T. H. (2022, December). Deep reinforcement learning methods for automation forex trading. In 2022 RIVF International Conference on Computing and Communication Technologies (RIVF) (pp. 671-676). IEEE.","DOI":"10.1109\/RIVF55975.2022.10013861"},{"issue":"10","key":"10.1016\/j.cie.2026.112048_b0070","doi-asserted-by":"crossref","first-page":"3080","DOI":"10.1080\/00207543.2018.1535205","article-title":"A reinforcement learning based approach for multi-projects scheduling in cloud manufacturing","volume":"57","author":"Chen","year":"2019","journal-title":"International Journal of Production Research"},{"issue":"4","key":"10.1016\/j.cie.2026.112048_b0075","doi-asserted-by":"crossref","first-page":"836","DOI":"10.1016\/j.dcan.2022.06.008","article-title":"Twin delayed deep deterministic policy gradient-based intelligent computation offloading for IoT","volume":"9","author":"Chen","year":"2023","journal-title":"Digital Communications and Networks"},{"issue":"6","key":"10.1016\/j.cie.2026.112048_b0080","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1504\/IJCSM.2015.073597","article-title":"Comparative analysis of swarm intelligence and heuristic priority rules for solving multi-project scheduling problem","volume":"6","author":"Chen","year":"2015","journal-title":"International Journal of Computing Science and Mathematics"},{"issue":"1","key":"10.1016\/j.cie.2026.112048_b0085","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1007\/s13755-023-00212-3","article-title":"A deep reinforcement learning-based wireless body area network offloading optimization strategy for healthcare services","volume":"11","author":"Chen","year":"2023","journal-title":"Health Information Science and Systems"},{"issue":"13","key":"10.1016\/j.cie.2026.112048_b0090","doi-asserted-by":"crossref","first-page":"1214","DOI":"10.1002\/rnc.1164","article-title":"AQ\u2010Learning\u2010based method applied to stochastic resource constrained project scheduling with new project arrivals","volume":"17","author":"Choi","year":"2007","journal-title":"International Journal of Robust and Nonlinear Control: IFAC-Affiliated Journal"},{"key":"10.1016\/j.cie.2026.112048_b0095","series-title":"In Proceedings of the 3rd international conference on vision, image and signal processing","first-page":"1","article-title":"Twin-delayed ddpg: A deep reinforcement learning technique to model a continuous movement of an intelligent robot agent","author":"Dankwa","year":"2019"},{"key":"10.1016\/j.cie.2026.112048_b0100","doi-asserted-by":"crossref","DOI":"10.1016\/j.autcon.2023.104958","article-title":"Extensions of the resource-constrained project scheduling problem","volume":"153","author":"Ding","year":"2023","journal-title":"Automation in Construction"},{"key":"10.1016\/j.cie.2026.112048_b0105","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106693","article-title":"Twin-delayed deep deterministic policy gradient algorithm for the energy management of microgrids","volume":"125","author":"Dom\u00ednguez-Barbero","year":"2023","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.cie.2026.112048_b0110","volume":"Vol. 24","author":"Dong","year":"2020"},{"key":"10.1016\/j.cie.2026.112048_b0115","article-title":"Resource-constrained multi-project scheduling problems considering time-dependent reliability of resources: A new immune genetic local search algorithm","author":"Farahmand-Mehr","year":"2025","journal-title":"Kybernetes"},{"key":"10.1016\/j.cie.2026.112048_b0120","doi-asserted-by":"crossref","unstructured":"Fradi, A., & Benali, M. (2024, September). Multi-project Scheduling Problem with Limited Preemption and Ordinary Feeding Precedence Relations. In IFIP International Conference on Advances in Production Management Systems (pp. 537-551). Cham: Springer Nature Switzerland.","DOI":"10.1007\/978-3-031-71645-4_36"},{"key":"10.1016\/j.cie.2026.112048_b0125","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2021.107402","article-title":"A combined multi-agent system for distributed multi-project scheduling problems","volume":"107","author":"Fu","year":"2021","journal-title":"Applied Soft Computing"},{"key":"10.1016\/j.cie.2026.112048_b0130","unstructured":"Fujimoto, S., Hoof, H., & Meger, D. (2018, July). Addressing function approximation error in actor-critic methods. In International conference on machine learning (pp. 1587-1596). PMLR."},{"issue":"12","key":"10.1016\/j.cie.2026.112048_b0135","doi-asserted-by":"crossref","first-page":"10638","DOI":"10.1109\/TNNLS.2022.3170070","article-title":"Distributed energy trading and scheduling among microgrids via multiagent reinforcement learning","volume":"34","author":"Gao","year":"2022","journal-title":"IEEE transactions on neural networks and learning systems"},{"issue":"3","key":"10.1016\/j.cie.2026.112048_b0140","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1016\/j.ejor.2016.07.024","article-title":"A multi-threaded local search algorithm and computer implementation for the multi-mode, resource-constrained multi-project scheduling problem","volume":"256","author":"Geiger","year":"2017","journal-title":"European Journal of Operational Research"},{"issue":"10","key":"10.1016\/j.cie.2026.112048_b0145","doi-asserted-by":"crossref","first-page":"13837","DOI":"10.1007\/s11227-024-05933-0","article-title":"Energy-efficient resource-constrained multi-project scheduling problem with generalized precedence relations and multi-skilled resources","volume":"80","author":"Goudarzi","year":"2024","journal-title":"The Journal of Supercomputing"},{"issue":"5","key":"10.1016\/j.cie.2026.112048_b0150","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1007\/s00287-023-01556-6","article-title":"Fully dynamic reorder policies with deep reinforcement learning for multi-echelon inventory management","volume":"46","author":"Hammler","year":"2023","journal-title":"Informatik Spektrum"},{"issue":"1","key":"10.1016\/j.cie.2026.112048_b0155","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ejor.2021.05.004","article-title":"An updated survey of variants and extensions of the resource-constrained project scheduling problem","volume":"297","author":"Hartmann","year":"2022","journal-title":"European Journal of operational research"},{"key":"10.1016\/j.cie.2026.112048_b0160","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2020.106857","article-title":"Resource-constrained multi-project scheduling with activity and time flexibility","volume":"150","author":"Hauder","year":"2020","journal-title":"Computers & Industrial Engineering"},{"issue":"6","key":"10.1016\/j.cie.2026.112048_b0165","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1111\/j.1475-3995.2007.00614.x","article-title":"A multi\u2010agent system for the decentralized resource\u2010constrained multi\u2010project scheduling problem","volume":"14","author":"Homberger","year":"2007","journal-title":"International Transactions in Operational Research"},{"issue":"2","key":"10.1016\/j.cie.2026.112048_b0170","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1016\/j.ejor.2022.01.018","article-title":"Integrated multi-project planning and scheduling-a multiagent approach","volume":"302","author":"He","year":"2022","journal-title":"European Journal of Operational Research"},{"issue":"5","key":"10.1016\/j.cie.2026.112048_b0175","doi-asserted-by":"crossref","first-page":"2451","DOI":"10.3934\/jimo.2020077","article-title":"Tabu search and simulated annealing for resource\u2013constrained multi-project scheduling to minimize maximal cash flow gap","volume":"17","author":"He","year":"2021","journal-title":"Journal of Industrial & Management Optimization"},{"issue":"1","key":"10.1016\/j.cie.2026.112048_b0180","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.ejor.2023.02.029","article-title":"Tabu search for dedicated resource-constrained multiproject scheduling to minimise the maximal cash flow gap under uncertainty","volume":"310","author":"He","year":"2023","journal-title":"European Journal of Operational Research"},{"issue":"8","key":"10.1016\/j.cie.2026.112048_b0185","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.1080\/01605682.2018.1489340","article-title":"A project scheduling problem with spatial resource constraints and a corresponding guided local search algorithm","volume":"70","author":"Hu","year":"2019","journal-title":"Journal of the Operational Research Society"},{"key":"10.1016\/j.cie.2026.112048_b0190","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/01605682.2025.2589327","article-title":"Priority rule-based heuristics for distributed multi-project scheduling considering global resource failures","author":"Hu","year":"2025","journal-title":"Journal of the Operational Research Society"},{"issue":"8","key":"10.1016\/j.cie.2026.112048_b0195","doi-asserted-by":"crossref","first-page":"2525","DOI":"10.3390\/s24082525","article-title":"Inspection robot navigation based on improved TD3 algorithm","volume":"24","author":"Huang","year":"2024","journal-title":"Sensors"},{"key":"10.1016\/j.cie.2026.112048_b0200","article-title":"Solving resource-constrained multi-project environment under different activity assumptions","volume":"232","author":"Issa","year":"2021","journal-title":"International Journal of Production Economics"},{"issue":"3","key":"10.1016\/j.cie.2026.112048_b0205","doi-asserted-by":"crossref","first-page":"2245","DOI":"10.1007\/s12351-021-00633-6","article-title":"A bi-objective model for scheduling of multiple projects under multi-skilled workforce for distributed load energy usage","volume":"22","author":"Javanmard","year":"2022","journal-title":"Operational Research"},{"key":"10.1016\/j.cie.2026.112048_b0210","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1016\/j.neucom.2014.05.070","article-title":"Reinforcement learning strategies for A-team solving the resource-constrained project scheduling problem","volume":"146","author":"J\u0119drzejowicz","year":"2014","journal-title":"Neurocomputing"},{"key":"10.1016\/j.cie.2026.112048_b0215","doi-asserted-by":"crossref","unstructured":"J\u0119drzejowicz, P., & Ratajczak-Ropel, E. (2015, May). Reinforcement learning strategy for solving the MRCPSP by a team of agents. In International Conference on Intelligent Decision Technologies (pp. 537-548). Cham: Springer International Publishing.","DOI":"10.1007\/978-3-319-19857-6_46"},{"key":"10.1016\/j.cie.2026.112048_b0220","doi-asserted-by":"crossref","DOI":"10.1016\/j.autcon.2023.104817","article-title":"Adaptive control of resource flow to optimize construction work and cash flow via online deep reinforcement learning","volume":"150","author":"Jiang","year":"2023","journal-title":"Automation in Construction"},{"issue":"5","key":"10.1016\/j.cie.2026.112048_b0225","doi-asserted-by":"crossref","DOI":"10.1061\/(ASCE)AS.1943-5525.0001426","article-title":"An integrated tracking control approach based on reinforcement learning for a continuum robot in space capture missions","volume":"35","author":"Jiang","year":"2022","journal-title":"Journal of Aerospace Engineering"},{"key":"10.1016\/j.cie.2026.112048_b0230","doi-asserted-by":"crossref","unstructured":"Joo, B., & Chua, P. (2017). Multimode resource-constrained multi-project scheduling with ad hoc activity splitting. In 2017 IEEE International conference on industrial engineering and engineering management (IEEM) (pp. 2261\u20132265). IEEE.","DOI":"10.1109\/IEEM.2017.8290294"},{"key":"10.1016\/j.cie.2026.112048_b0235","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1016\/j.jmsy.2023.02.002","article-title":"Look-ahead based reinforcement learning for robotic flow shop scheduling","volume":"68","author":"Kim","year":"2023","journal-title":"Journal of Manufacturing Systems"},{"issue":"20","key":"10.1016\/j.cie.2026.112048_b0240","doi-asserted-by":"crossref","first-page":"5359","DOI":"10.3390\/en13205359","article-title":"Automatic P2P energy trading model based on reinforcement learning using long short-term delayed reward","volume":"13","author":"Kim","year":"2020","journal-title":"Energies"},{"key":"10.1016\/j.cie.2026.112048_b0245","doi-asserted-by":"crossref","unstructured":"Kong, F., & Chen, K. (2025). Three-phase CPLEX with quota auction mechanism for dedicated resource-constrained multi-project scheduling problem with calendar constraints. Engineering, Construction and Architectural Management.","DOI":"10.1108\/ECAM-07-2024-0970"},{"issue":"1","key":"10.1016\/j.cie.2026.112048_b0250","doi-asserted-by":"crossref","first-page":"633","DOI":"10.3390\/app13010633","article-title":"Empirical analysis of automated stock trading using deep reinforcement learning","volume":"13","author":"Kong","year":"2023","journal-title":"Applied Sciences"},{"issue":"2","key":"10.1016\/j.cie.2026.112048_b0255","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1007\/s00291-008-0144-5","article-title":"Managing and modelling general resource transfers in (multi-) project scheduling","volume":"32","author":"Kr\u00fcger","year":"2010","journal-title":"OR Spectrum"},{"issue":"19","key":"10.1016\/j.cie.2026.112048_b0260","doi-asserted-by":"crossref","first-page":"5812","DOI":"10.1080\/00207543.2021.1972179","article-title":"Explainable reinforcement learning in production control of job shop manufacturing system","volume":"60","author":"Kuhnle","year":"2022","journal-title":"International Journal of Production Research"},{"issue":"7","key":"10.1016\/j.cie.2026.112048_b0265","doi-asserted-by":"crossref","first-page":"2346","DOI":"10.1080\/00207543.2021.1887533","article-title":"Reinforcement learning for robotic flow shop scheduling with processing time variations","volume":"60","author":"Lee","year":"2022","journal-title":"International Journal of Production Research"},{"key":"10.1016\/j.cie.2026.112048_b0270","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.117796","article-title":"A multi-action deep reinforcement learning framework for flexible Job-shop scheduling problem","volume":"205","author":"Lei","year":"2022","journal-title":"Expert Systems with Applications"},{"issue":"10","key":"10.1016\/j.cie.2026.112048_b0275","article-title":"A multi-agent system for distributed multi-project scheduling with two-stage decomposition","volume":"13","author":"Li","year":"2018","journal-title":"PLoS One1"},{"issue":"1","key":"10.1016\/j.cie.2026.112048_b0280","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.ejor.2015.04.015","article-title":"Solving stochastic resource-constrained project scheduling problems by closed-loop approximate dynamic programming","volume":"246","author":"Li","year":"2015","journal-title":"European Journal of Operational Research"},{"issue":"1","key":"10.1016\/j.cie.2026.112048_b0285","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1080\/00207543.2020.1788737","article-title":"Dynamic resource levelling in projects under uncertainty","volume":"61","author":"Li","year":"2023","journal-title":"International Journal of Production Research"},{"key":"10.1016\/j.cie.2026.112048_b0290","doi-asserted-by":"crossref","DOI":"10.1016\/j.cor.2024.106623","article-title":"A branch-and-bound algorithm for the proactive resource-constrained project scheduling problem with a robustness maximization objective","volume":"166","author":"Li","year":"2024","journal-title":"Computers & Operations Research"},{"key":"10.1016\/j.cie.2026.112048_b0295","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.124794","article-title":"A new resource-constrained project scheduling problem with ladder-type carbon trading prices and its algorithm based on deep reinforcement learning","volume":"255","author":"Liu","year":"2024","journal-title":"Expert Systems with Applications"},{"issue":"2","key":"10.1016\/j.cie.2026.112048_b0300","doi-asserted-by":"crossref","DOI":"10.1061\/(ASCE)CP.1943-5487.0000816","article-title":"Robust dual-level optimization framework for resource\u2013constrained multiproject scheduling for a prefabrication facility in construction","volume":"33","author":"Liu","year":"2019","journal-title":"Journal of Computing in Civil Engineering"},{"key":"10.1016\/j.cie.2026.112048_b0305","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2024.110843","article-title":"Resource allocation models and heuristics for the multi-project scheduling with global resource transfers and local resource constraints","volume":"200","author":"Liu","year":"2025","journal-title":"Computers & industrial engineering"},{"key":"10.1016\/j.cie.2026.112048_b0310","doi-asserted-by":"crossref","unstructured":"Min, C. H., & Song, J. B. (2019, June). End-to-end robot manipulation using demonstration-guided goal strategie. In 2019 16th International Conference on Ubiquitous Robots (UR) (pp. 159-164). IEEE.","DOI":"10.1109\/URAI.2019.8768699"},{"issue":"7540","key":"10.1016\/j.cie.2026.112048_b0315","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"10.1016\/j.cie.2026.112048_b0320","article-title":"A dynamic learning-based genetic algorithm for scheduling resource-constrained projects with alternative subgraphs","volume":"113316","author":"Nekoueian","year":"2025","journal-title":"Applied Soft Computing"},{"key":"10.1016\/j.cie.2026.112048_b0325","first-page":"11767","article-title":"Softmax deep double deterministic policy gradients","volume":"33","author":"Pan","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"5","key":"10.1016\/j.cie.2026.112048_b0330","doi-asserted-by":"crossref","first-page":"180","DOI":"10.3390\/a17050180","article-title":"Maximizing net present value for resource constraint project scheduling problems with payments at event occurrences using approximate dynamic programming","volume":"17","author":"Phuntsho","year":"2024","journal-title":"Algorithms"},{"issue":"2","key":"10.1016\/j.cie.2026.112048_b0335","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1016\/j.ejor.2019.01.063","article-title":"A survey of hybrid metaheuristics for the resource-constrained project scheduling problem","volume":"280","author":"Pellerin","year":"2020","journal-title":"European Journal of Operational Research"},{"issue":"4","key":"10.1016\/j.cie.2026.112048_b0340","doi-asserted-by":"crossref","first-page":"1098","DOI":"10.1007\/s40435-023-01227-0","article-title":"Decentralized multi-agent control of a three-tank hybrid system based on twin delayed deep deterministic policy gradient reinforcement learning algorithm","volume":"12","author":"Rajasekhar","year":"2024","journal-title":"International Journal of Dynamics and Control"},{"issue":"5\u20136","key":"10.1016\/j.cie.2026.112048_b0345","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1080\/01969722.2017.1418269","article-title":"Experimental evaluation of agent-based approaches to solving multi-mode resource-constrained project scheduling problem","volume":"49","author":"Ratajczak-Ropel","year":"2018","journal-title":"Cybernetics and Systems"},{"issue":"3","key":"10.1016\/j.cie.2026.112048_b0350","doi-asserted-by":"crossref","first-page":"1637","DOI":"10.1007\/s10479-023-05403-5","article-title":"A Benders decomposition algorithm for the multi-mode resource-constrained multi-project scheduling problem with uncertainty","volume":"339","author":"Sadeghloo","year":"2024","journal-title":"Ann. Oper. Res."},{"key":"10.1016\/j.cie.2026.112048_b0355","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2020.114479","article-title":"A reinforcement learning based multi-method approach for stochastic resource constrained project scheduling problems","volume":"169","author":"Sallam","year":"2021","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.cie.2026.112048_b0360","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2022.119123","article-title":"Multi-agent deep deterministic policy gradient algorithm for peer-to-peer energy trading considering distribution network constraints","volume":"317","author":"Samende","year":"2022","journal-title":"Applied Energy"},{"issue":"3","key":"10.1016\/j.cie.2026.112048_b0365","doi-asserted-by":"crossref","first-page":"958","DOI":"10.1016\/j.ejor.2022.09.033","article-title":"Resource-constrained multi-project scheduling problem: A survey","volume":"309","author":"S\u00e1nchez","year":"2023","journal-title":"European Journal of Operational Research"},{"issue":"4","key":"10.1016\/j.cie.2026.112048_b0370","doi-asserted-by":"crossref","first-page":"1411","DOI":"10.1080\/00207543.2020.1857450","article-title":"Performance evaluation of scheduling policies for the dynamic and stochastic resource-constrained multi-project scheduling problem","volume":"60","author":"Satic","year":"2022","journal-title":"International Journal of Production Research"},{"issue":"2","key":"10.1016\/j.cie.2026.112048_b0375","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1016\/j.ejor.2023.10.046","article-title":"A simulation-based approximate dynamic programming approach to dynamic and stochastic resource-constrained multi-project scheduling problem","volume":"315","author":"Satic","year":"2024","journal-title":"European Journal of Operational Research"},{"issue":"2","key":"10.1016\/j.cie.2026.112048_b0380","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1007\/s00291-015-0419-6","article-title":"On the efficient modeling and solution of the multi-mode resource-constrained project scheduling problem with generalized precedence relations","volume":"38","author":"Schnell","year":"2016","journal-title":"OR Spectrum"},{"key":"10.1016\/j.cie.2026.112048_b0385","doi-asserted-by":"crossref","unstructured":"Sewak, M., & Sewak, M. (2019). Deterministic policy gradient and the ddpg: Deterministic-policy-gradient-based approaches. Deep Reinforcement Learning: Frontiers of Artificial Intelligence, 173-184.","DOI":"10.1007\/978-981-13-8285-7_13"},{"key":"10.1016\/j.cie.2026.112048_b0390","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ins.2017.10.041","article-title":"A Q-learning-based memetic algorithm for multi-objective dynamic software project scheduling","volume":"428","author":"Shen","year":"2018","journal-title":"Information Sciences"},{"key":"10.1016\/j.cie.2026.112048_b0395","doi-asserted-by":"crossref","first-page":"1548","DOI":"10.1007\/s10458-017-9370-z","article-title":"A multi-unit combinatorial auction based approach for decentralized multi-project scheduling","volume":"31","author":"Song","year":"2017","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"10.1016\/j.cie.2026.112048_b0400","doi-asserted-by":"crossref","DOI":"10.1016\/j.egyai.2022.100215","article-title":"Deep reinforcement learning for the optimized operation of large amounts of distributed renewable energy assets","volume":"11","author":"Specht","year":"2023","journal-title":"Energy and AI"},{"issue":"2","key":"10.1016\/j.cie.2026.112048_b0405","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/0377-2217(93)90185-P","article-title":"Hierarchical models for multi-project planning and scheduling","volume":"64","author":"Speranza","year":"1993","journal-title":"European Journal of Operational Research"},{"issue":"3","key":"10.1016\/j.cie.2026.112048_b0410","doi-asserted-by":"crossref","DOI":"10.1061\/(ASCE)CO.1943-7862.0001613","article-title":"Zero-one formulation for a partial resource-constrained project scheduling problem with generalized precedence relations","volume":"145","author":"Su","year":"2019","journal-title":"Journal of Construction Engineering and Management"},{"key":"10.1016\/j.cie.2026.112048_b0415","series-title":"Deep deterministic policy gradient algorithm: A systematic review","author":"Sumiea","year":"2024"},{"key":"10.1016\/j.cie.2026.112048_b0420","doi-asserted-by":"crossref","unstructured":"Sun, J., Zhang, F., Wang, R., & Si, J. (2021, September). Research on resource-constrained multi-project scheduling problem considering resource substitution based on ant colony optimization. In 2021 International Conference on E-Commerce and E-Management (ICECEM) (pp. 69-73). IEEE.","DOI":"10.1109\/ICECEM54757.2021.00022"},{"issue":"2","key":"10.1016\/j.cie.2026.112048_b0425","doi-asserted-by":"crossref","first-page":"10493","DOI":"10.1016\/j.ifacol.2020.12.2794","article-title":"Reinforcement learning for resource constrained project scheduling problem with activity iterations and crashing","volume":"53","author":"Sung","year":"2020","journal-title":"IFAC-PapersOnLine"},{"issue":"4","key":"10.1016\/j.cie.2026.112048_b0430","doi-asserted-by":"crossref","first-page":"982","DOI":"10.1049\/rpg2.12650","article-title":"Low\u2010carbon economic dispatch of the combined heat and power\u2010virtual power plants: A improved deep reinforcement learning\u2010based approach","volume":"17","author":"Tan","year":"2023","journal-title":"IET Renewable Power Generation"},{"key":"10.1016\/j.cie.2026.112048_b0435","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1007\/s10951-015-0422-4","article-title":"An integer programming approach to the multimode resource-constrained multiproject scheduling problem","volume":"19","author":"Toffolo","year":"2016","journal-title":"Journal of Scheduling"},{"issue":"1","key":"10.1016\/j.cie.2026.112048_b0440","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1007\/s10479-023-05784-7","article-title":"Solving a real-life multi-skill resource-constrained multi-project scheduling problem","volume":"338","author":"Torba","year":"2024","journal-title":"Ann. Oper. Res."},{"key":"10.1016\/j.cie.2026.112048_b0445","article-title":"Examining a multi-skilled project scheduling problem for shipyard industry through operational and tactical perspectives","volume":"107150","author":"T\u00fcrk","year":"2025","journal-title":"Computers & Operations Research"},{"issue":"16","key":"10.1016\/j.cie.2026.112048_b0450","doi-asserted-by":"crossref","first-page":"e6266","DOI":"10.1002\/cpe.6266","article-title":"A graphical processing unit\u2010based parallel hybrid genetic algorithm for resource\u2010constrained multi\u2010project scheduling problem","volume":"33","author":"Uysal","year":"2021","journal-title":"Concurrency and Computation: Practice and Experience"},{"key":"10.1016\/j.cie.2026.112048_b0455","doi-asserted-by":"crossref","DOI":"10.1016\/j.cor.2020.105163","article-title":"A column generation-based diving heuristic to solve the multi-project personnel staffing problem with calendar constraints and resource sharing","volume":"128","author":"Van Den Eeckhout","year":"2021","journal-title":"Computers & Operations Research"},{"issue":"1","key":"10.1016\/j.cie.2026.112048_b0460","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.ejor.2023.07.043","article-title":"Hybrid differential evolution algorithm for the resource constrained project scheduling problem with a flexible project structure and consumption and production of resources","volume":"313","author":"Van der Beek","year":"2024","journal-title":"European Journal of Operational Research"},{"issue":"3","key":"10.1016\/j.cie.2026.112048_b0465","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1007\/s10951-020-00651-w","article-title":"Resource-constrained multi-project scheduling: Benchmark datasets and decoupled scheduling","volume":"23","author":"Van Eynde","year":"2020","journal-title":"Journal of Scheduling"},{"issue":"3","key":"10.1016\/j.cie.2026.112048_b0470","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1016\/j.ejor.2021.10.006","article-title":"New summary measures and datasets for the multi-project scheduling problem","volume":"299","author":"Van Eynde","year":"2022","journal-title":"European Journal of Operational Research"},{"issue":"10","key":"10.1016\/j.cie.2026.112048_b0475","doi-asserted-by":"crossref","first-page":"3465","DOI":"10.1007\/s00500-017-3003-y","article-title":"A generic heuristic for multi-project scheduling problems with global and local resource constraints (RCMPSP)","volume":"23","author":"Villaf\u00e1\u00f1ez","year":"2019","journal-title":"Soft Computing"},{"key":"10.1016\/j.cie.2026.112048_b0480","doi-asserted-by":"crossref","unstructured":"Vishal, M., Satija, Y., & Babu, B. S. (2021, December). Trading agent for the Indian stock market scenario using Actor-Critic based reinforcement learning. In 2021 IEEE international conference on computation system and information technology for sustainable solutions (CSITSS) (pp. 1-5). IEEE.","DOI":"10.1109\/CSITSS54238.2021.9683467"},{"key":"10.1016\/j.cie.2026.112048_b0485","first-page":"1","article-title":"Design patterns of deep reinforcement learning models for job shop scheduling problems","author":"Wang","year":"2024","journal-title":"Journal of Intelligent Manufacturing"},{"key":"10.1016\/j.cie.2026.112048_b0490","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijepes.2024.110326","article-title":"Twin delayed deep deterministic policy gradient based stochastic optimal dispatch of hydro and wind power considering the uncertainty of wind power in power-time dimensions","volume":"163","author":"Wang","year":"2024","journal-title":"International Journal of Electrical Power & Energy Systems"},{"key":"10.1016\/j.cie.2026.112048_b0495","doi-asserted-by":"crossref","DOI":"10.1016\/j.cor.2022.106095","article-title":"Solving non-permutation flow-shop scheduling problem via a novel deep reinforcement learning approach","volume":"151","author":"Wang","year":"2023","journal-title":"Computers & Operations Research"},{"key":"10.1016\/j.cie.2026.112048_b0500","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1007\/s10951-014-0401-1","article-title":"A learning-based optimization approach to multi-project scheduling","volume":"18","author":"Wauters","year":"2015","journal-title":"Journal of Scheduling"},{"key":"10.1016\/j.cie.2026.112048_b0505","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/j.apm.2021.03.048","article-title":"An approximate dynamic programming approach to project scheduling with uncertain resource availabilities","volume":"97","author":"Xie","year":"2021","journal-title":"Applied Mathematical Modelling"},{"issue":"12","key":"10.1016\/j.cie.2026.112048_b0510","doi-asserted-by":"crossref","first-page":"1996","DOI":"10.3390\/buildings15121996","article-title":"Learning-enhanced differential evolution for multi-mode resource-constrained multi-project scheduling problem in industrial prefabrication","volume":"15","author":"Xing","year":"2025","journal-title":"Buildings"},{"key":"10.1016\/j.cie.2026.112048_b0515","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2023.111201","article-title":"Bi-objective multi-mode resource-constrained multi-project scheduling using combined NSGA II and Q-learning algorithm","volume":"152","author":"Yang","year":"2024","journal-title":"Applied Soft Computing"},{"issue":"02\u201314-03-0033","key":"10.1016\/j.cie.2026.112048_b0520","doi-asserted-by":"crossref","first-page":"409","DOI":"10.4271\/02-14-03-0033","article-title":"Sensitivity analysis of reinforcement learning-based hybrid electric vehicle powertrain control","volume":"14","author":"Yao","year":"2021","journal-title":"SAE International Journal of Commercial Vehicles"},{"issue":"3","key":"10.1016\/j.cie.2026.112048_b0525","doi-asserted-by":"crossref","first-page":"1631","DOI":"10.1111\/itor.13392","article-title":"A two\u2010layer approach for solving robust decentralized multiproject scheduling problem with multi\u2010skilled staff","volume":"31","author":"You","year":"2024","journal-title":"International Transactions in Operational Research"},{"issue":"3","key":"10.1016\/j.cie.2026.112048_b0530","doi-asserted-by":"crossref","DOI":"10.1063\/1.5021839","article-title":"A bi-level multi-agent system model for decentralized multi-project scheduling of wind power plants","volume":"10","author":"Zhang","year":"2018","journal-title":"Journal of Renewable and Sustainable Energy"},{"issue":"3","key":"10.1016\/j.cie.2026.112048_b0535","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1016\/j.ejor.2024.07.018","article-title":"A three-dimensional spatial resource-constrained project scheduling problem: Model and heuristic","volume":"319","author":"Zhang","year":"2024","journal-title":"European Journal of Operational Research"},{"key":"10.1016\/j.cie.2026.112048_b0540","article-title":"A literature review of reinforcement learning methods applied to job-shop scheduling problems","volume":"106929","author":"Zhang","year":"2024","journal-title":"Computers & Operations Research"},{"key":"10.1016\/j.cie.2026.112048_b0545","doi-asserted-by":"crossref","DOI":"10.1016\/j.enconman.2022.116454","article-title":"Twin delayed deep deterministic policy gradient-based deep reinforcement learning for energy management of fuel cell vehicle integrating durability information of powertrain","volume":"274","author":"Zhang","year":"2022","journal-title":"Energy Conversion and Management"},{"issue":"1","key":"10.1016\/j.cie.2026.112048_b0550","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1007\/s10479-024-05854-4","article-title":"A robust multi-project scheduling problem under a resource dedication-transfer policy","volume":"337","author":"Zhao","year":"2024","journal-title":"Ann. Oper. Res."},{"key":"10.1016\/j.cie.2026.112048_b0555","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.115593","article-title":"New closed-loop approximate dynamic programming for solving stochastic decentralized multi-project scheduling problem with resource transfers","volume":"185","author":"Zhao","year":"2021","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.cie.2026.112048_b0560","doi-asserted-by":"crossref","unstructured":"Zhao, X., Song, W., Li, Q., Shi, H., Kang, Z., & Zhang, C. (2022, December). A deep reinforcement learning approach for resource-constrained project scheduling. In 2022 IEEE Symposium Series on Computational Intelligence (SSCI) (pp. 1226-1234). IEEE.","DOI":"10.1109\/SSCI51031.2022.10022122"},{"key":"10.1016\/j.cie.2026.112048_b0565","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2023.109802","article-title":"The application of heterogeneous graph neural network and deep reinforcement learning in hybrid flow shop scheduling problem","volume":"187","author":"Zhao","year":"2024","journal-title":"Computers & Industrial Engineering"},{"issue":"1","key":"10.1016\/j.cie.2026.112048_b0570","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1109\/TCOMM.2022.3221422","article-title":"DDPG-based joint time and energy management in ambient backscatter-assisted hybrid underlay CRNs","volume":"71","author":"Zheng","year":"2022","journal-title":"IEEE Transactions on Communications"},{"key":"10.1016\/j.cie.2026.112048_b0575","doi-asserted-by":"crossref","DOI":"10.1016\/j.autcon.2023.104948","article-title":"Time-and resource-based robust scheduling algorithms for multi-skilled projects","volume":"153","author":"Zhentao","year":"2023","journal-title":"Automation in Construction"}],"container-title":["Computers & Industrial Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0360835226002494?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0360835226002494?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T06:55:28Z","timestamp":1779519328000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0360835226002494"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":115,"alternative-id":["S0360835226002494"],"URL":"https:\/\/doi.org\/10.1016\/j.cie.2026.112048","relation":{},"ISSN":["0360-8352"],"issn-type":[{"value":"0360-8352","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A novel deep reinforcement learning method for solving resource-constrained multi-project scheduling problem: twin delayed deep deterministic policy gradient","name":"articletitle","label":"Article Title"},{"value":"Computers & Industrial Engineering","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cie.2026.112048","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":"112048"}}