Deep reinforcement learning for inventory control: A roadmap

2021/07/16 by Robert N. Boute, Robert Boute, Joren Gijsbrechts +2 · 5 citations
Business, Management and Accounting · Computer Science · Engineering · #Reinforcement Learning in Robotics #Supply Chain and Inventory Management #Traffic control and management

paper · doi:10.1016/j.ejor.2021.07.016

openalex publication_date 2021/07/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01

Abstract

Deep reinforcement learning (DRL) has shown great potential for sequential decision-making, including early developments in inventory control. Yet, the abundance of choices that come with designing a DRL algorithm, combined with the intense computational effort to tune and evaluate each choice, may hamper their application in practice. This paper describes the key design choices of DRL algorithms to facilitate their implementation in inventory control. We also shed light on possible future research avenues that may elevate the current state-of-the-art of DRL applications for inventory control and broaden their scope by leveraging and improving on the structural policy insights within inventory research. Our discussion and roadmap may also spur future research in other domains within operations management.

Citations

• Practical Bayesian Optimization of Machine Learning Algorithms
• Multilayer feedforward networks are universal approximators
• ImageNet classification with deep convolutional neural networks
• Challenges of Real-World Reinforcement Learning
• Mastering Atari, Go, chess and shogi by planning with a learned model
• Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems

Cited by

• Deep Reinforcement Learning for inventory optimization with non-stationary uncertain demand
• Optimal outbound shipment policy for an inventory system with advance demand information
• Reward shaping to improve the performance of deep reinforcement learning in perishable inventory management
• Combining deep reinforcement learning and multi-stage stochastic programming to address the supply chain inventory management problem
• Deep reinforcement learning for demand fulfillment in online retail