Paper Title
Determining the Effectiveness of RL in Tackling Inventory Control Complexities

Abstract
Determining inventory control (IC) with uncertain demand becomes challenging when inventory analysis is done with multiple products with different lead times, including non-zero ones. This paper aims to verify the effectiveness of two Deep Reinforcement learning (DRL) algorithms and their impact on IC complexities. Contributions include comparing two DRL algorithms with a static reorder policy (s, Q) through a data-driven approach. The extent of the application of the algorithms and their effectiveness in complex IC scenarios is quantified and potential extensions involving more complexities are identified. Specific future research directions and novel approaches are recommended. Keywords - Reinforcement Learning, Inventory Control Complexities, DRL categorization