Applying and Comparing Policy Gradient Methods to Multi-echelon Supply Chains with Uncertain Demands and Lead Times

Alves, Júlio César Camargo; Silva, Diego Mello da; Mateus, Geraldo Robson

doi:10.1007/978-3-030-87897-9_21

Cited by 4 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, most mainstream RL methods are based on this architecture. Alves and Silva [19] used a shared policy in a supply chain collaboration environment to compare the performance of different single-agent RL algorithms, such as Deep Deterministic Policy Gradient (DDPG) [24], Soft Actor-Critic (SAC) [25], and Proximal Policy Optimization (PPO) [26], and the implementation results showed that the PPO algorithm performed the best. In this study, all homogenous agents used the same policy for inventory management.…”

Section: Inventory Management Methods With Actor-critic Rlmentioning

confidence: 99%

“…As different participants in the supply chain play different roles and require different types and quantities of materials for inventory management, some differences exist in inventory management methods and goals. Suppose a single-agent RL algorithm [18] or homogeneous MARL algorithm [19] is used to address this problem. In that case, the model's efficiency will be limited to some extent.…”

Section: Methods Overviewmentioning

confidence: 99%

See 1 more Smart Citation

A Supply Chain Inventory Management Method for Civil Aircraft Manufacturing Based on Multi-Agent Reinforcement Learning

Piao,

Zhang,

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Effective supply chain inventory management is crucial for large-scale manufacturing industries such as civil aircraft and automobile manufacturing to ensure efficient manufacturing. Generally, the main manufacturer makes the annual inventory management plan, and contacts with suppliers when some material is approaching critical inventory level according to the actual production schedule, which increases the difficulty of inventory management. In recent years, many researchers have focused on using reinforcement learning method to study inventory management problems. Current approaches were mainly designed for the supply chain with single-node multi-material or multi-node single-material mode, which are not suitable to the civil aircraft manufacturing supply chain with multi-node multi-material mode. To deal with this problem, we formulated the problem as a partially observable Markov decision process (POMDP) model and proposed a multi-agent reinforcement learning method for supply chain inventory management, in which the dual-policy and information transmission mechanism was designed to help the supply chain participant improve the global information utilization efficiency of the supply chain and the coordination efficiency with other participants. The experiment results show that our method has about 45% performance improvement on efficiency compared with current reinforcement learning-based methods.

show abstract

Section: Inventory Management Methods With Actor-critic Rlmentioning

confidence: 99%

Section: Methods Overviewmentioning

confidence: 99%

A Supply Chain Inventory Management Method for Civil Aircraft Manufacturing Based on Multi-Agent Reinforcement Learning

Piao,

Zhang,

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

Cloud material handling systems: a cyber-physical system to enable dynamic resource allocation and digital interoperability

Aron,

Sgarbossa,

Ballot

et al. 2023

J Intell Manuf

View full text Add to dashboard Cite

The existing logistics practices frequently lack the ability to effectively handle disruptions. Recent research called for dynamic, digital-driven approaches that can help prioritise allocation of logistics resources to design more adaptive and sustainable logistics networks. The purpose of this study is to explore inter-dependencies between physical and digital assets to examine how cyber-physical systems could enable interoperability in logistics networks. The paper provides an overview of the existing literature on cyber-physical applications in logistics and proposes a conceptual model of a Cloud Material Handling System. The model allows leveraging the use of digital technologies to capture and process real-time information about a logistics network with the aim to dynamically allocate material handling resources and promote asset and infrastructure sharing. The model describes how cloud computing, machine learning and real-time information can be utilised to dynamically allocate material handling resources to product flows. The adoption of the proposed model can increase efficiency, resilience and sustainability of logistics practices. Finally, the paper offers several promising research avenues for extending this work.

show abstract

On the Integration of Google Cloud and SAP HANA for Adaptive Supply Chain in Retailing

Nahhas

Haertel

Daase

et al. 2023

Procedia Computer Science

View full text Add to dashboard Cite

Applying and Comparing Policy Gradient Methods to Multi-echelon Supply Chains with Uncertain Demands and Lead Times

Cited by 4 publications

References 6 publications

A Supply Chain Inventory Management Method for Civil Aircraft Manufacturing Based on Multi-Agent Reinforcement Learning

A Supply Chain Inventory Management Method for Civil Aircraft Manufacturing Based on Multi-Agent Reinforcement Learning

Cloud material handling systems: a cyber-physical system to enable dynamic resource allocation and digital interoperability

On the Integration of Google Cloud and SAP HANA for Adaptive Supply Chain in Retailing

Contact Info

Product

Resources

About