Please use this identifier to cite or link to this item: http://hdl.handle.net/10125/50044

Deep Multi-Agent Reinforcement Learning using DNN-Weight Evolution to Optimize Supply Chain Performance

File Size Format  
paper0157.pdf 1.02 MB Adobe PDF View/Open

Item Summary

Title:Deep Multi-Agent Reinforcement Learning using DNN-Weight Evolution to Optimize Supply Chain Performance
Authors:Fuji, Taiki
Ito, Kiyoto
Matsumoto, Kohsei
Yano, Kazuo
Keywords:Intelligent Decision Support for Logistics and Supply Chain Management
Deep learning, Evolutionary computation, Multi-agent reinforcement learning, Multi-agent system, Supply chain management
Date Issued:03 Jan 2018
Abstract:To develop a supply chain management (SCM) system that performs optimally for both each entity in the chain and the entire chain, a multi-agent reinforcement learning (MARL) technique has been developed. To solve two problems of the MARL for SCM (building a Markov decision processes for a supply chain and avoiding learning stagnation in a way similar to the "prisoner's dilemma"), a learning management method with deep-neural-network (DNN)-weight evolution (LM-DWE) has been developed. By using a beer distribution game (BDG) as an example of a supply chain, experiments with a four-agent system were performed. Consequently, the LM-DWE successfully solved the above two problems and achieved 80.0% lower total cost than expert players of the BDG.
Pages/Duration:10 pages
URI:http://hdl.handle.net/10125/50044
ISBN:978-0-9981331-1-9
DOI:10.24251/HICSS.2018.157
Rights:Attribution-NonCommercial-NoDerivatives 4.0 International
https://creativecommons.org/licenses/by-nc-nd/4.0/
Appears in Collections: Intelligent Decision Support for Logistics and Supply Chain Management


Please email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.

This item is licensed under a Creative Commons License Creative Commons