Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management
This addresses inventory management for businesses with multiple stock-keeping units, but it is incremental as it builds on existing multi-agent reinforcement learning approaches.
The paper tackles the inventory management problem with shared resource constraints by formulating it as a Shared-Resource Stochastic Game and proposing the Context-aware Decentralized PPO algorithm, which accelerates learning compared to standard MARL methods.
In this paper, we consider the inventory management (IM) problem where we need to make replenishment decisions for a large number of stock keeping units (SKUs) to balance their supply and demand. In our setting, the constraint on the shared resources (such as the inventory capacity) couples the otherwise independent control for each SKU. We formulate the problem with this structure as Shared-Resource Stochastic Game (SRSG)and propose an efficient algorithm called Context-aware Decentralized PPO (CD-PPO). Through extensive experiments, we demonstrate that CD-PPO can accelerate the learning procedure compared with standard MARL algorithms.