As a supplement to Zhu et al. (2020), this document consists of five parts. First, it provides technical proofs of some theoretical results in Zhu et al. (2020). Second, it introduces some preliminary results on stochastic distribution systems with fixed shipment costs. Third, it provides some...

We apply Multi-Agent Deep Reinforcement Learning (MADRL) to inventory management problems with multiple echelons and evaluate MADRL's performance to minimize the overall costs of a supply chain. We also examine whether the upfront-only information-sharing mechanism used in MADRL helps alleviate...