MARLIM: Multi-Agent Reinforcement Learning for Inventory Management

TL;DR

This paper introduces MARLIM, a multi-agent reinforcement learning framework designed to optimize inventory management in supply chains, effectively balancing supply and demand under uncertainty.

Contribution

The paper presents a novel reinforcement learning approach for inventory management, utilizing multi-agent systems to improve decision-making in supply chain contexts.

Findings

Reinforcement learning outperforms traditional methods in inventory control.

MARLIM effectively handles stochastic demands and lead-times.

Numerical experiments validate the approach on real data.

Abstract

Maintaining a balance between the supply and demand of products by optimizing replenishment decisions is one of the most important challenges in the supply chain industry. This paper presents a novel reinforcement learning framework called MARLIM, to address the inventory management problem for a single-echelon multi-products supply chain with stochastic demands and lead-times. Within this context, controllers are developed through single or multiple agents in a cooperative setting. Numerical experiments on real data demonstrate the benefits of reinforcement learning methods over traditional baselines.