Think4SCND: Reinforcement Learning With Thinking Model for Dynamic Supply Chain Network Design
Supply chain network design is a critical strategic challenge that significantly influences operational efficiency and competitiveness in the global marketplace. This paper introduces Think4SCND, a novel deep reinforcement learning framework that addresses the dynamic complexities of supply chain ne...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10812729/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533386370318336 |
|---|---|
| author | Pan Li Shaochen Ren Qun Zhang Xuran Wang Yang Liu |
| author_facet | Pan Li Shaochen Ren Qun Zhang Xuran Wang Yang Liu |
| author_sort | Pan Li |
| collection | DOAJ |
| description | Supply chain network design is a critical strategic challenge that significantly influences operational efficiency and competitiveness in the global marketplace. This paper introduces Think4SCND, a novel deep reinforcement learning framework that addresses the dynamic complexities of supply chain network design by integrating a Supply Chain Transformer Network with a Thinking Model. Our approach formulates the supply chain network design problem as a Markov Decision Process, developing an architecture capable of handling mixed discrete-continuous action spaces. The core innovation lies in the Thinking Model, which enhances the Supply Chain Transformer Network’s ability to reason about future states and evaluate decision sequences, enabling more informed and forward-looking decision-making. We propose an end-to-end training algorithm that effectively combines model-free reinforcement learning with model-based planning. Extensive experiments on both synthetic and real-world datasets show that Think4SCND significantly outperforms state-of-the-art baselines, achieving near-optimal solutions with a fraction of the computational cost. The framework demonstrates superior adaptability to disruptions and strong generalization capabilities, successfully transferring knowledge from medium-sized problems to larger, unseen instances. |
| format | Article |
| id | doaj-art-0d5cf401a62e4c50b47796856e3bc087 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-0d5cf401a62e4c50b47796856e3bc0872025-01-16T00:01:32ZengIEEEIEEE Access2169-35362024-01-011219597419598510.1109/ACCESS.2024.352143910812729Think4SCND: Reinforcement Learning With Thinking Model for Dynamic Supply Chain Network DesignPan Li0Shaochen Ren1Qun Zhang2Xuran Wang3https://orcid.org/0009-0001-1626-5527Yang Liu4https://orcid.org/0009-0008-5087-8133Business School, University of Hull, Hull, U.K.Tandon School of Engineering, New York University, New York, NY, USADepartment of Statistics and Biostatistics, California State University, East Bay, Hayward, CA, USADepartment of Computer and Information Science, University of Pennsylvania, Philadelphia, PA, USADepartment of Computer Science, Worcester Polytechnic Institute, Worcester, MA, USASupply chain network design is a critical strategic challenge that significantly influences operational efficiency and competitiveness in the global marketplace. This paper introduces Think4SCND, a novel deep reinforcement learning framework that addresses the dynamic complexities of supply chain network design by integrating a Supply Chain Transformer Network with a Thinking Model. Our approach formulates the supply chain network design problem as a Markov Decision Process, developing an architecture capable of handling mixed discrete-continuous action spaces. The core innovation lies in the Thinking Model, which enhances the Supply Chain Transformer Network’s ability to reason about future states and evaluate decision sequences, enabling more informed and forward-looking decision-making. We propose an end-to-end training algorithm that effectively combines model-free reinforcement learning with model-based planning. Extensive experiments on both synthetic and real-world datasets show that Think4SCND significantly outperforms state-of-the-art baselines, achieving near-optimal solutions with a fraction of the computational cost. The framework demonstrates superior adaptability to disruptions and strong generalization capabilities, successfully transferring knowledge from medium-sized problems to larger, unseen instances.https://ieeexplore.ieee.org/document/10812729/Supply chain network designinventory managementreinforcement learningthinking modeltransformer network |
| spellingShingle | Pan Li Shaochen Ren Qun Zhang Xuran Wang Yang Liu Think4SCND: Reinforcement Learning With Thinking Model for Dynamic Supply Chain Network Design IEEE Access Supply chain network design inventory management reinforcement learning thinking model transformer network |
| title | Think4SCND: Reinforcement Learning With Thinking Model for Dynamic Supply Chain Network Design |
| title_full | Think4SCND: Reinforcement Learning With Thinking Model for Dynamic Supply Chain Network Design |
| title_fullStr | Think4SCND: Reinforcement Learning With Thinking Model for Dynamic Supply Chain Network Design |
| title_full_unstemmed | Think4SCND: Reinforcement Learning With Thinking Model for Dynamic Supply Chain Network Design |
| title_short | Think4SCND: Reinforcement Learning With Thinking Model for Dynamic Supply Chain Network Design |
| title_sort | think4scnd reinforcement learning with thinking model for dynamic supply chain network design |
| topic | Supply chain network design inventory management reinforcement learning thinking model transformer network |
| url | https://ieeexplore.ieee.org/document/10812729/ |
| work_keys_str_mv | AT panli think4scndreinforcementlearningwiththinkingmodelfordynamicsupplychainnetworkdesign AT shaochenren think4scndreinforcementlearningwiththinkingmodelfordynamicsupplychainnetworkdesign AT qunzhang think4scndreinforcementlearningwiththinkingmodelfordynamicsupplychainnetworkdesign AT xuranwang think4scndreinforcementlearningwiththinkingmodelfordynamicsupplychainnetworkdesign AT yangliu think4scndreinforcementlearningwiththinkingmodelfordynamicsupplychainnetworkdesign |