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,...

We explore using supervised learning with custom loss functions for multi-period inventory problems with feature-driven demand. This method directly considers feature information such as promotions and trends to make periodic order decisions, does not require distributional assumptions on...