A Transformer-Enhanced Multi-Agent Reinforcement Learning Model for Resilience Optimization in Educational Equipment Manufacturing Supply Chains
DOI:
https://doi.org/10.4108/eetsis.14151Keywords:
Transformer, Multi-agent reinforcement learning, Supply chain resilience, Disruption-riskAbstract
INTRODUCTION: Educational equipment manufacturing supply chains are vulnerable to demand fluctuations, equipment failures, logistics disruptions, and cross-node risk propagation, while conventional approaches often separate state prediction from recovery decision-making.
OBJECTIVES: This study proposes TMARL-ESCR, a Transformer-enhanced multi-agent reinforcement learning framework for supply chain resilience optimization.
METHODS: The model represents suppliers, manufacturers, logistics providers, and distribution centers as a dynamic network and uses a Transformer to capture long-range temporal dependencies and cross-node interactions. Multitask prediction heads estimate future demand, logistics lead time, available capacity, and disruption risk, and these predictions are fused with current states to support coordinated recovery decisions. Under a centralized training and decentralized execution framework, multiple agents jointly optimize procurement, production, transportation, and inventory reallocation through local-global rewards and explicit operational constraints.
RESULTS:The prediction module achieves a demand WMAPE of 14.38% and a disruption-risk AUC of 0.941. The complete model reaches a 95.2% order fulfillment rate, a 7.1-day recovery time, a 0.5% constraint violation rate, and a resilience score of 0.892. Compared with Transformer-MAPPO, TMARL-ESCR reduces recovery time by 19.3% and improves the resilience score by 5.9%.
CONCLUSION: Experiments integrating M5 Forecasting, AI4I 2020, LaDe, and an SCML-based simulation environment evaluate predictive accuracy and resilience optimization under multiple disruption scenarios, demonstrating improved proactive recovery and coordinated resilience under complex disruptions.
References
[1] Grossman G M, Helpman E, Lhuillier H. Supply chain resilience: Should policy promote international diversification or reshoring?[J]. Journal of Political Economy, 2023, 131(12): 3462–3496.
[2] Safari A, Balicevac Al Ismail V, Parast M, et al. Supply chain risk and resilience in startups, SMEs, and large enterprises: A systematic review and directions for research[J]. The International Journal of Logistics Management, 2024, 35(2): 680–709.
[3] Tian S, Wu L, Ciano M P, et al. Enhancing innovativeness and performance of the manufacturing supply chain through datafication: The role of resilience[J]. Computers & Industrial Engineering, 2024, 188: 109841.
[4] Mukherjee S, Baral M M, Nagariya R, et al. Artificial intelligence-based supply chain resilience for improving firm performance in emerging markets[J]. Journal of Global Operations and Strategic Sourcing, 2024, 17(3): 516–540.
[5] Riad M, Naimi M, Okar C. Enhancing supply chain resilience through artificial intelligence: Developing a comprehensive conceptual framework for AI implementation and supply chain optimization[J]. Logistics, 2024, 8(4): 111.
[6] Samadhiya A, Yadav S, Kumar A, et al. The influence of artificial intelligence techniques on disruption management: Does supply chain dynamism matter?[J]. Technology in Society, 2023, 75: 102394.
[7] Tirkolaee E B, Torkayesh A E, Tavana M, et al. An integrated decision support framework for resilient vaccine supply chain network design[J]. Engineering Applications of Artificial Intelligence, 2023, 126: 106945.
[8] Ashraf M, Eltawil A, Ali I. Disruption detection for a cognitive digital supply chain twin using hybrid deep learning[J]. Operational Research, 2024, 24: 23.
[9] Sadeghi R K, Ojha D, Kaur P, et al. Explainable artificial intelligence and agile decision-making in supply chain cyber resilience[J]. Decision Support Systems, 2024, 180: 114194.
[10] Jackson I, Ivanov D, Dolgui A, et al. Generative artificial intelligence in supply chain and operations management: A capability-based framework for analysis and implementation[J]. International Journal of Production Research, 2024, 62(17): 6120–6145.
[11] Singh D, Sharma A, Singh R K, et al. Augmenting supply chain resilience through AI and big data[J]. Business Process Management Journal, 2025, 31(2): 631–657.
[12] Jauhar S K, Harinath S, Krishnaswamy V, et al. Explainable artificial intelligence to improve the resilience of perishable product supply chains by leveraging customer characteristics[J]. Annals of Operations Research, 2025, 354: 103–142.
[13] Ceptureanu E G, Ferraro G, Ceptureanu S I, et al. Impact of artificial intelligence and blockchain on supply chain resilience under influence of change management[J]. Soft Computing, 2025, 29(7): 3617–3625.
[14] Singh D, Sharma A, Singh R K, et al. Artificial intelligence enabled supply chain resilience: Insights from FMCG industry[J]. Journal of Global Operations and Strategic Sourcing, 2025, 18(2): 414–441.
[15] Tang H, Wu K, Zhou J. Smarter supply chains, stronger resilience? The impact of AI on preparation, response, and recovery[J]. Economics Letters, 2025, 254: 112488.
[16] Guo X, Chen Y, Xie J, et al. Research on supply chain resilience mechanism of AI-enabled manufacturing enterprises—based on organizational change perspective[J]. Scientific Reports, 2025, 15: 31177.
[17] Yue X, Kang M, Zhang Y. The impact of artificial intelligence usage on supply chain resilience in manufacturing firms: A moderated mediation model[J]. Journal of Manufacturing Technology Management, 2025, 36: 759–776.
[18] Pan H, Zou N, Wang R, et al. Artificial intelligence usage and supply chain resilience: An organizational information processing theory perspective[J]. Systems, 2025, 13(9): 724.
[19] Nawaz W, Li Z. Complexity to resilience: Machine learning models for enhancing supply chains and resilience in the Middle Eastern trade corridor nations[J]. Systems, 2025, 13(3): 209.
[20] Wu D, Li T, Cai H, et al. Machine learning-based prediction of resilience in green agricultural supply chains: Influencing factors analysis and model construction[J]. Systems, 2025, 13(7): 615.
[21] Douaioui K, Oucheikh R, Benmoussa O, et al. Machine learning and deep learning models for demand forecasting in supply chain management: A critical review[J]. Applied System Innovation, 2024, 7(5): 93.
[22] Aldahmani E, Alzubi A, Iyiola K. Demand forecasting in supply chain using uni-regression deep approximate forecasting model[J]. Applied Sciences, 2024, 14(18): 8110.
[23] Oliveira J M, Ramos P. Evaluating the effectiveness of time series Transformers for demand forecasting in retail[J]. Mathematics, 2024, 12(17): 2728.
[24] Caetano R, Oliveira J M, Ramos P. Transformer-based models for probabilistic time series forecasting with explanatory variables[J]. Mathematics, 2025, 13(5): 814.
[25] Alrashdi I, Abd El-Aziz R M, Taloba A I, et al. Hybrid TCN-Transformer model for predicting sustainable food supply and ensuring resilience[J]. Alexandria Engineering Journal, 2025, 127: 380–391.
[26] Geevers K, van Hezewijk L, Mes M R K. Multi-echelon inventory optimization using deep reinforcement learning[J]. Central European Journal of Operations Research, 2024, 32: 653–683.
[27] Mousa M, van de Berg D, Kotecha N, et al. An analysis of multi-agent reinforcement learning for decentralized inventory control systems[J]. Computers & Chemical Engineering, 2024, 188: 108783.
[28] Zhang B, Tan W J, Cai W, et al. Leveraging multi-agent reinforcement learning for digital transformation in supply chain inventory optimization[J]. Sustainability, 2024, 16(22): 9996.
[29] Liu X, Hu M, Peng Y, et al. Multi-agent deep reinforcement learning for multi-echelon inventory management[J]. Production and Operations Management, 2025, 34(7): 1836–1856.
[30] Hu J, Xia L, Huang T, et al. A multi-agent deep reinforcement learning approach for multi-echelon inventory optimization and its application to the beer game[J]. Transportation Research Part E: Logistics and Transportation Review, 2025, 203: 104367.
[31] Zarghami S A, Dumrak J. Evaluating vulnerability of supply chain networks to capacity reduction[J]. Global Journal of Flexible Systems Management, 2024, 25: 629–646
[32] Yang S, Ogawa Y, Ikeuchi K, et al. Post-hazard supply chain disruption: Predicting firm-level sales using graph neural network[J]. International Journal of Disaster Risk Reduction, 2024, 110: 104664.
[33] Tang X, Wang Y, Liu X, et al. Federated graph neural network for privacy-preserved supply chain data sharing[J]. Applied Soft Computing, 2025, 168: 112475.
[34] Wang Z, Ran H, Ren J, et al. PWDformer: Deformable transformer for long-term series forecasting[J]. Pattern Recognition, 2024, 147: 110118.
[35] Zhao J, Chu F, Xie L, et al. A survey of transformer networks for time series forecasting[J]. Computer Science Review, 2026, 60: 100883.
[36] Dehaybe H, Catanzaro D, Chevalier P. Deep Reinforcement Learning for inventory optimization with non-stationary uncertain demand[J]. European Journal of Operational Research, 2024, 314(2): 433-445.
[37] Kaynov I, van Knippenberg M, Menkovski V, et al. Deep Reinforcement Learning for One-Warehouse Multi-Retailer inventory management[J]. International Journal of Production Economics, 2024, 267: 109088.
[38] Kim B, Kim J G, Lee S. A multi-agent reinforcement learning model for inventory transshipments under supply chain disruption[J]. IISE Transactions, 2024, 56(7): 715-728.
[39] Kotecha N, del Rio Chanona A. Leveraging graph neural networks and multi-agent reinforcement learning for inventory control in supply chains[J]. Computers & Chemical Engineering, 2025, 199: 109111.
[40] Burtea R, Tsay C. Constrained continuous-action reinforcement learning for supply chain inventory management[J]. Computers & Chemical Engineering, 2024, 181: 108518.
[41] Stranieri F, Fadda E, Stella F. Combining deep reinforcement learning and multi-stage stochastic programming to address the supply chain inventory management problem[J]. International Journal of Production Economics, 2024, 268: 109099.
[42] Wang J, Swartz C L E, Huang K. Risk-averse supply chain management via robust reinforcement learning[J]. Computers & Chemical Engineering, 2025, 192: 108912.
[43] Temizöz T, Imdahl C, Dijkman R, et al. Deep Controlled Learning for Inventory Control[J]. European Journal of Operational Research, 2025, 324(1): 104-117.
[44] Yu C, Velu A, Vinitsky E, et al. The surprising effectiveness of PPO in cooperative multi-agent games[C]. Advances in Neural Information Processing Systems. 2022, 35.
[45] Wen M, Kuba J, Lin R, et al. Multi-agent reinforcement learning is a sequence modeling problem[C]. Advances in Neural Information Processing Systems. 2022, 35.
[46] Achiam J, Held D, Tamar A, et al. Constrained Policy Optimization[C]. Proceedings of the 34th International Conference on Machine Learning. PMLR, 2017, 70: 22–31.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Yiquan Kong
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
