Tail-Risk-Aware Decentralized Supplier Policies for Low-Carbon Procurement Under Correlated Disruptions

Authors

  • Sabrina Kapoor Mays Business School, Texas A&M University, USA
  • Samuel Thompson Carlson School of Management, University of Minnesota Twin Cities, USA
  • Ibrahim Perez Carlson School of Management, University of Minnesota Twin Cities, USA
  • Emily Foster Eli Broad College of Business, Michigan State University, USA

DOI:

https://doi.org/10.54097/wj82kb36

Keywords:

Green supply chain, CVaR, multi-agent reinforcement learning, carbon uncertainty, resilience, stochastic procurement

Abstract

Green public procurement must balance purchase cost, carbon intensity and service continuity under supplier disruptions whose emissions outcomes are uncertain. Building on the multi-agent sourcing formulation of GRACE, we develop a decentralized, shared-parameter supplier policy coordinated by a transparent public rationing rule and trained with a CVaR-regularized policy gradient (CVaR-PG) that penalizes the worst 20% of episode losses under noisy carbon proxies and cluster-correlated failures. Over 720 evaluation episodes per regime from four training seeds, CVaR-PG lowers pooled upper-tail loss relative to mean-only learning by 3.1% under high-severity shocks (1.258 versus 1.299) and by 1.9% under a held-out failure family (1.299 versus 1.325), with seed-level paired intervals reported for each contrast. Comparisons with reserve-aware and emissions-first rules show that transparent rules with access to supplier reserve information remain strong benchmarks for tail risk and carbon, identifying the coordination interface as the main lever for further gains. The study provides a reproducible benchmark for risk-aware multi-agent procurement under emissions uncertainty.

Downloads

Download data is not yet available.

References

[1] Srivastava, S. K. (2007). Green supply-chain management: A state-of-the-art literature review. International Journal of Management Reviews, 9(1), 53–80. https://doi.org/10.1111/j.1468-2370.2007.00202.x DOI: https://doi.org/10.1111/j.1468-2370.2007.00202.x

[2] Yue, X., & Zhu, R. (2024). An explainable hybrid machine learning framework for cash-flow-conditioned multi-horizon liquidity risk early warning: An SME-oriented benchmark study. World Journal of Management Science, 2(1), 63–72. DOI: https://doi.org/10.61784/wms4120

[3] Benjaafar, S., Li, Y., & Daskin, M. (2013). Carbon footprint and the management of supply chains: Insights from simple models. IEEE Transactions on Automation Science and Engineering, 10(1), 99–116. https://doi.org/10.1109/TASE.2012.2203304 DOI: https://doi.org/10.1109/TASE.2012.2203304

[4] Ivanov, D., & Dolgui, A. (2020). Viability of intertwined supply networks: Extending the supply chain resilience angles towards survivability. A position paper motivated by COVID-19 outbreak. International Journal of Production Research, 58(10), 2904–2915. https://doi.org/10.1080/00207543.2020.1750727 DOI: https://doi.org/10.1080/00207543.2020.1750727

[5] Hosseini, S., Ivanov, D., & Dolgui, A. (2019). Review of quantitative methods for supply chain resilience analysis. Transportation Research Part E, 125, 285–307. https://doi.org/10.1016/j.tre.2019.03.001 DOI: https://doi.org/10.1016/j.tre.2019.03.001

[6] Simchi-Levi, D., et al. (2015). Identifying risks and mitigating disruptions in the automotive supply chain. Interfaces, 45(5), 375–390. https://doi.org/10.1287/inte.2015.0804 DOI: https://doi.org/10.1287/inte.2015.0804

[7] Zobel, C. W. (2011). Representing perceived tradeoffs in defining disaster resilience. Decision Support Systems, 50(2), 394–403. https://doi.org/10.1016/j.dss.2010.10.001 DOI: https://doi.org/10.1016/j.dss.2010.10.001

[8] Kamalahmadi, M., & Parast, M. M. (2016). A review of the literature on the principles of enterprise and supply chain resilience: Major findings and directions for future research. International Journal of Production Economics, 171, 116–133. https://doi.org/10.1016/j.ijpe.2015.10.023 DOI: https://doi.org/10.1016/j.ijpe.2015.10.023

[9] Zhou, F. (2026). Moment-constrained side-force allocation for wind-assisted merchant ships: Hydrodynamic performance of retractable anti-leeway fins and flap rudders. Innovation and Technology Studies, 3(1), 27–41. DOI: https://doi.org/10.61784/its4027

[10] Gunasekaran, A., et al. (2017). Big data and predictive analytics for supply chain and organizational performance. Journal of Business Research, 70, 308–317. https://doi.org/10.1016/j.jbusres.2016.08.004 DOI: https://doi.org/10.1016/j.jbusres.2016.08.004

[11] Bian, M., Li, P., Lin, Y., Wang, Y., & Teng, D. (2026). Assessing green public supply chains resilience under carbon neutrality goals: A multi-agent reinforcement learning framework. IEEE Access, 14, 120495–120510. https://doi.org/10.1109/ACCESS.2026.3720389 DOI: https://doi.org/10.1109/ACCESS.2026.3720389

[12] Kim, B., Kim, J. G., & Lee, S. (2024). A multi-agent reinforcement learning model for inventory transshipments under supply chain disruption. IISE Transactions, 56(7), 715–728. https://doi.org/10.1080/24725854.2023.2217248 DOI: https://doi.org/10.1080/24725854.2023.2217248

[13] Kotecha, N., & del Rio Chanona, A. (2025). Leveraging graph neural networks and multi-agent reinforcement learning for inventory control in supply chains. Computers & Chemical Engineering, 199, 109111. https://doi.org/10.1016/j.compchemeng.2025.109111 DOI: https://doi.org/10.1016/j.compchemeng.2025.109111

[14] Wang, Q., & Yang, Y. (2024). Carbon trading supply chain management based on constrained deep reinforcement learning. Autonomous Agents and Multi-Agent Systems, 38, 38. https://doi.org/10.1007/s10458-024-09669-2 DOI: https://doi.org/10.1007/s10458-024-09669-2

[15] Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., & Whiteson, S. (2018). Counterfactual multi-agent policy gradients. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1), 2974–2982. https://doi.org/10.1609/aaai.v32i1.11794 DOI: https://doi.org/10.1609/aaai.v32i1.11794

[16] Oroojlooyjadid, A., Nazari, M., Snyder, L. V., & Takáč, M. (2022). A deep Q-network for the beer game: Deep reinforcement learning for inventory optimization. Manufacturing & Service Operations Management, 24(1), 285–304. https://doi.org/10.1287/msom.2020.0939 DOI: https://doi.org/10.1287/msom.2020.0939

[17] Teng, D. (2025). TRIAD: Deadline- and reliability-aware scheduling for post-earthquake structural assessment workflows. World Journal of Engineering Research, 3(6), 55–66. DOI: https://doi.org/10.61784/wjer4124

[18] Tamar, A., Chow, Y., Ghavamzadeh, M., & Mannor, S. (2015). Policy gradient for coherent risk measures. Advances in Neural Information Processing Systems, 28, 1468–1476.

[19] García, J., & Fernández, F. (2015). A comprehensive survey on safe reinforcement learning. Journal of Machine Learning Research, 16(42), 1437–1480.

[20] Achiam, J., Held, D., Tamar, A., & Abbeel, P. (2017). Constrained policy optimization. In Proceedings of the 34th International Conference on Machine Learning (Vol. PMLR 70, pp. 22–31).

[21] Chen, J., Han, X., Zhang, X., & Yang, Y. (2023). Exact concept-level explanations for early detection of financial misstatements. Eurasia Journal of Science and Technology, 5(2), 34–48. DOI: https://doi.org/10.61784/ejst4162

[22] Rashid, T., et al. (2020). Monotonic value function factorisation for deep multi-agent reinforcement learning. Journal of Machine Learning Research, 21(178), 1–51.

[23] Papadopoulos, T., et al. (2017). The role of big data in explaining disaster resilience in supply chains for sustainability. Journal of Cleaner Production, 142, 1108–1118. https://doi.org/10.1016/j.jclepro.2016.03.059 DOI: https://doi.org/10.1016/j.jclepro.2016.03.059

[24] Ding, W., Ming, Z., Wang, G., Yan, Y., & Zhang, D. (2026). Multi-agent reinforcement learning-based resilience reconfiguration approach of supply chain system-of-systems under disruption risks. International Journal of Production Economics, 109995. https://doi.org/10.1016/j.ijpe.2026.109995 DOI: https://doi.org/10.1016/j.ijpe.2026.109995

[25] Liu, J., Wang, J., & Lin, H. (2025). Coordinated Physics-Informed Multi-Agent Reinforcement Learning for Risk-Aware Supply Chain Optimization. IEEE Access. https://doi.org/10.1109/ACCESS.2025.3629716 DOI: https://doi.org/10.1109/ACCESS.2025.3629716

[26] Li, P., et al. (2024). Think4SCND: Reinforcement Learning With Thinking Model for Dynamic Supply Chain Network Design. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3521439 DOI: https://doi.org/10.1109/ACCESS.2024.3521439

Downloads

Published

09-11-2026

Issue

Section

Articles

How to Cite

Kapoor, S., Thompson, S., Perez, I., & Foster, E. (2026). Tail-Risk-Aware Decentralized Supplier Policies for Low-Carbon Procurement Under Correlated Disruptions. International Journal of World Economic Research, 3(3), 44-50. https://doi.org/10.54097/wj82kb36