The Supply Chain Transportation and Route Planning Under Deep Reinforcement Learning

The Supply Chain Transportation and Route Planning Under Deep Reinforcement Learning

Xiaohe Xie (School of Art, Southeast University, China), Ya Qin (School of Fine Arts, Nanjing Normal University, China), Xuan Zhang (School of Art, Southeast University, China), Hongming Li (College of Education, University of Florida, USA), and Abby Yurong Zhang (Caelus Capital, New York, USA)
Copyright: © 2025 |Pages: 27
DOI: 10.4018/JOEUC.369158
Article PDF Download
Open access articles are freely available for download

Abstract

As concerns over environmental pollution and the reduction of greenhouse gas emissions intensify, sustainable strategies in supply chain transportation are critical. This paper proposes a novel approach to optimizing transportation routes and reducing carbon emissions in a green supply chain using deep reinforcement learning. The research targets a three-tier green supply chain consisting of manufacturers, third-party logistics providers (3PL), and retailers. First, a carbon reduction model for transportation is established, accounting for both product greenness and carbon emissions that influence demand. The study then introduces a Proximal Policy Optimization (PPO)-based contract model, combining cost-sharing and profit-sharing mechanisms between retailers and logistics providers to incentivize eco-friendly practices.
Article Preview
Top

Introduction

Currently, the trend of global climate change is becoming increasingly significant, which has attracted widespread attention from scholars and business managers to the theory and practice of green supply chain management for art.

With the global trend toward green and low-carbon development, the art supply chain also needs to integrate the principles of green and low-carbon development. Due to the niche nature of art production, glass products, ceramic products, textiles, and wooden products can easily cause adverse environmental impacts during the production process. In the field of supply chain management, the fulfillment of social responsibility must coexist with a balance between low-carbon environmental goals and economic goals. This has become an inevitable trend in the development of the supply chain (Oliveira et al., 2018). Consumers' high attention to social responsibility and fierce market competition are the main driving forces for promoting green management and reducing carbon emissions in the supply chain (Su et al., 2019; Yang et al., 2019). Under traditional decentralized decision-making, each member in the art supply chain pursues the maximization of individual profits, resulting in overall profits far below the level achievable under centralized decision-making. However, in actual operation, various enterprises in the art supply chain collaborate and rely on each other. The carbon emission levels of each enterprise in the art supply chain will affect the overall carbon reduction targets of the entire supply chain. At the same time, these emission levels will also affect the market sales of final art products, thereby affecting the economic benefits of various enterprises in the supply chain. Therefore, the urgent task is to promote cooperation among enterprises in various links of the green supply chain and jointly achieve carbon reduction. A model of how this can be achieved is shown in Figure 1.

Figure 1.

Example of a complete industry chain for art products

JOEUC.369158.f01

The supply chain is a complex network composed of multiple decision-making entities. In the entire supply chain, encompassing production, distribution, and delivery, the enterprises at each link are not independent entities but rather exist in interdependent relationships (Wu, 2022). Each node enterprise's carbon emission levels impact the overall carbon reduction effectiveness of the supply chain.

In recent years, numerous scholars have explored various aspects of green supply chains. Ghosh and Shah (2012) focused on a two-tier supply chain consisting of manufacturers and retailers, establishing multiple decision models to investigate the impact of greening costs and consumer sensitivity to green products. Martin-Herran and Taboubi (2015) studied how green supply chains can devise optimal sales strategies when carbon emissions affect market demand and product prices. Basiri and Heydari (2017) explored coordination issues in a two-stage green supply chain, where the surveyed supply chain sells both a non-green traditional product and a new alternative green product. By creating a mathematical model to coordinate product sales prices, green quality, and sales effort levels, they concluded that collaborative models could stimulate demand for green products.

However, there is a “double marginalization effect” in green supply chains. To effectively mitigate the impact of this effect on the economic benefits of participants in the supply chain, the selection and application of scientifically sound supply chain contract methods have become an inevitable choice for its rapid development. Additionally, there are currently two coordination methods in supply chain management: centralized decision-making and decentralized decision-making. Decentralized decision-making is more commonly used, but under this approach, each member in the supply chain aims to maximize its individual profit, resulting in the overall profit of the supply chain being much lower than that under centralized decision-making. Therefore, how to choose and design appropriate supply chain contracts for coordination has become a crucial research question.

Complete Article List

Search this Journal:
Reset
Volume 37: 1 Issue (2025)
Volume 36: 1 Issue (2024)
Volume 35: 3 Issues (2023)
Volume 34: 10 Issues (2022)
Volume 33: 6 Issues (2021)
Volume 32: 4 Issues (2020)
Volume 31: 4 Issues (2019)
Volume 30: 4 Issues (2018)
Volume 29: 4 Issues (2017)
Volume 28: 4 Issues (2016)
Volume 27: 4 Issues (2015)
Volume 26: 4 Issues (2014)
Volume 25: 4 Issues (2013)
Volume 24: 4 Issues (2012)
Volume 23: 4 Issues (2011)
Volume 22: 4 Issues (2010)
Volume 21: 4 Issues (2009)
Volume 20: 4 Issues (2008)
Volume 19: 4 Issues (2007)
Volume 18: 4 Issues (2006)
Volume 17: 4 Issues (2005)
Volume 16: 4 Issues (2004)
Volume 15: 4 Issues (2003)
Volume 14: 4 Issues (2002)
Volume 13: 4 Issues (2001)
Volume 12: 4 Issues (2000)
Volume 11: 4 Issues (1999)
Volume 10: 4 Issues (1998)
Volume 9: 4 Issues (1997)
Volume 8: 4 Issues (1996)
Volume 7: 4 Issues (1995)
Volume 6: 4 Issues (1994)
Volume 5: 4 Issues (1993)
Volume 4: 4 Issues (1992)
Volume 3: 4 Issues (1991)
Volume 2: 4 Issues (1990)
Volume 1: 3 Issues (1989)
View Complete Journal Contents Listing