Timezone: »

Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management
Yuandong Ding · Mingxiao Feng · Guozi Liu · Wei Jiang · Chuheng Zhang · Li Zhao · Lei Song · Houqiang Li · Yan Jin · Jiang Bian

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.

Author Information

Yuandong Ding (Huazhong University of Science and Technology)
Mingxiao Feng (University of Science and Technology of China)
Guozi Liu (Carnegie Mellon University)
Wei Jiang (University of Illinois at Urbana-Champaign)
Chuheng Zhang (Tsinghua University)
Li Zhao (Microsoft Research)
Lei Song (Microsoft)
Houqiang Li (University of Science and Technology of China)
Yan Jin (Huazhong University of Science & Technology)
Jiang Bian (Microsoft)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors