… We focus on deep reinforcement learning (DRL), the subfield of machine learning that
develops “prescriptions” or policies for sequential decisionmaking problems. DRL employs deep …

… Deep reinforcement learning for inventory optimization with non-stationary uncertain … Can
deep reinforcement learning improve inventory management? performance on lost sales, dual-…

Is Deep Reinforcement Learning (DRL) effective at solving inventory problems? Given that
DRL has successfully been applied in computer games and robotics, supply chain …

… We consider both backlogging and lost-sales cases, and our goal … , we design a deep
reinforcement learning algorithm to obtain a … We also show that our deep reinforcement learning …

… a product’s sales period. By optimizing daily orders, lost sales opportunities can be avoided
… availability of sales operations by automatically determining appropriate order quantities. …

… and lost sales, we effectively tested the DRL approach on 120 unique backorder and 120
unique lost sales instances, each never encountered by the agents during the training phase. …

… The optimal policy for inventory models with lost sales and arbitrary lead times, for instance,
does not have a simple form, but it can be obtained numerically for small problems with short …

… 1 − p em demand is immediately lost and a lost sales penalty is incurred. With probability p
… Denote by C j ( t ) the costs for retailer j for period t : For lost sales we find C j ( t ) = p j L j ( t ) …

… In our study, we use deep reinforcement learning (DRL) to … DRL is a combination of deep
learning and reinforcement learning (… In more detail, the current sales price has a deeper effect …

… A3C algorithm for the lost sales problem but also surpasses … these listed applications of
deep reinforcement learning (DRL… We first test the DCL algorithm on lost sales inventory control…