This paper studies the applicability of a deep reinforcement learning approach to three
different multi-echelon inventory systems, with the objective of minimizing the holding and
backorder costs. First, we conduct an extensive literature review to map the current
applications of reinforcement learning in multi-echelon inventory systems. Next, we apply
our deep reinforcement learning method to three cases with different network structures
(linear, divergent, and general structures). The linear and divergent cases are derived from …

The operation of supply chains is a major cost driver for all manufacturing companies. It is
imperative to keep this cost at a minimum and the service level at a maximum to enable
companies to redirect investment to their core goals, such as the development of new drugs
in the healthcare industry. The field that deals with this task is called inventory management
and has served as an intensely studied research area for many decades. In practice,
companies often rely on parameterized reorder policies for the operation of inventory …