A Deep Q-Network Based on Radial Basis Functions for Multi-Echelon Inventory Management
This addresses inventory management problems for complex supply chains, offering an incremental improvement in DRL methods.
The paper tackles the challenge of deriving optimal ordering decisions in multi-echelon inventory management by developing a deep reinforcement learning model with a Q-network based on radial basis functions, demonstrating superior performance over base-stock policies and current DRL approaches in simulations.
This paper addresses a multi-echelon inventory management problem with a complex network topology where deriving optimal ordering decisions is difficult. Deep reinforcement learning (DRL) has recently shown potential in solving such problems, while designing the neural networks in DRL remains a challenge. In order to address this, a DRL model is developed whose Q-network is based on radial basis functions. The approach can be more easily constructed compared to classic DRL models based on neural networks, thus alleviating the computational burden of hyperparameter tuning. Through a series of simulation experiments, the superior performance of this approach is demonstrated compared to the simple base-stock policy, producing a better policy in the multi-echelon system and competitive performance in the serial system where the base-stock policy is optimal. In addition, the approach outperforms current DRL approaches.