Deep reinforcement learning (DRL) has proven to be an effective, general-purpose technology develop ‘good’ replenishment policies in inventory management. We show how transfer from existing, well-performing heuristics may stabilize the training process and improve performance of DRL control. While idea is general, we specifically implement potential-based reward shaping a deep Q-network algorit...

<p style='text-indent:20px;'>Perishable products like dairy products, vegetables, fruits, pharmaceuticals, etc. lose their freshness over time and become completely obsolete after a certain period. Customers generally prefer the fresh aged ones, leading perishable to have decreasing demand function with respect age. We analyze inventory management pricing decisions for these considering a...

This paper aims to develop a new bi-level game model for joint pricing and inventory decisions in competitive supply chain consisting of dominant manufacturer, who produces single perishable product from deteriorating raw materials, two follower retailers face nonlinear price-dependent demand operate under Cournot assumptions. Three levels warehousing including material warehouse, final retail ...

in this paper, we develop an inventory model for perishable items with random lifetime in a two-echelon production-distribution system. there is a manufacturer at the first stage that produces its product with a constant rate. deterioration in this stage is modeled via a two-parameter weibull distribution. at the second stage, the retailer places the order and receives the product instantly. th...

In this paper, we consider a two-commodity stochastic s , S perishable inventory system of the multiqueue Jackson network at service facility with reneging and jockeying customers. The waiting room capacity first queue is id="M2"> <mi...