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.
@article{arxiv.2212.07684,
title = {Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management},
author = {Yuandong Ding and Mingxiao Feng and Guozi Liu and Wei Jiang and Chuheng Zhang and Li Zhao and Lei Song and Houqiang Li and Yan Jin and Jiang Bian},
journal= {arXiv preprint arXiv:2212.07684},
year = {2022}
}