Inventory Control

Follow this topic Ask about this topic

Inventory control decides when and where to replenish or allocate goods when demand, lead times, shelf life, and shared capacity are uncertain. Methods range from base-stock rules and stochastic or robust optimization to contextual learning, censored-demand estimation, and reinforcement learning, including neural policies that enforce hard constraints. Work evaluates decisions by operational outcomes such as inventory cost, fill rate, and stockouts across retail, pharmaceutical, warehouse, and multi-echelon settings—not just forecast accuracy. A central tension is learning from incomplete sales data while providing reliable guarantees, and balancing scalable adaptive policies with transparency and dependable performance under shifts in demand.

Latest papers

34 papers2 papers in the last four weeks, down 67% on the four weeks before. 0.0% of all new papers.

DeepStock: Reinforcement Learning with Policy Regularizations for Inventory Management
Mar 20, 2026Yaqi Xie, Xinru Hao, Jiaxi Liu +4Inventory Control Reinforcement Learning
Booth School of Business, University of Chicago, Chicago, USA. · Taobao & Tmall Group, Hangzhou, China. · School of Economics, Sichuan University, Chengdu, China. +2
Beyond Accuracy: Evaluating Forecasting Models by Multi-Echelon Inventory Cost
Mar 17, 2026Swata Marik, Swayamjit Saha, Garga ChatterjeeInventory Control Time Series Forecasting
Department of Home Science, University of Calcutta, 20 E, Judges Court Road, Alipore, Kolkata, 700027, West Bengal, India. · Department of Computer Science and Engineering, Mississippi State University, 665 George Perry Street, Starkville, 39759, MS, USA. · Psychology Research Unit, Indian Statistical Institute Kolkata, 203, B.T. Road, Kolkata, 700108, West Bengal, India.
COOL-MC: Verifying and Explaining RL Policies for Platelet Inventory Management
Mar 2, 2026Dennis GrossInventory Control Reinforcement Learning
What is the Value of Censored Data? An Exact Analysis for the Data-driven Newsvendor
Feb 18, 2026Rachitesh Kumar, Omar MouchtakiInventory Control Minimax Regret
Carnegie Mellon University · New York University

Mar 20, 2026J/K move · Enter open · S save

DeepStock: Reinforcement Learning with Policy Regularizations for Inventory Management

Yaqi Xie, Xinru Hao, Jiaxi Liu, Will Ma+3

Booth School of Business, University of Chicago, Chicago, USA. · Taobao & Tmall Group, Hangzhou, China. · School of Economics, Sichuan University, Chengdu, China.+2

Inventory Control Reinforcement Learning Policy Learning Regularized RL

Open paper AskPDF arXiv

Deep Reinforcement Learning (DRL) provides a general-purpose methodology for training inventory policies that can leverage big data and compute. However, off-the-shelf implementations of DRL have seen mixed success, often plagued by high sensitivity to the hyperparameters used during training. In this paper, we show that by imposing policy regularizations, grounded in classical inventory concepts such as "Base Stock", we can significantly accelerate hyperparameter tuning and improve the final performance of several DRL methods. We report details from a 100% deployment of DRL with policy regularizations on Alibaba's e-commerce platform, Tmall. We also include extensive synthetic experiments, which show that policy regularizations reshape the narrative on what is the best DRL method for inventory management.

Latest papers

DeepStock: Reinforcement Learning with Policy Regularizations for Inventory Management

Beyond Accuracy: Evaluating Forecasting Models by Multi-Echelon Inventory Cost

COOL-MC: Verifying and Explaining RL Policies for Platelet Inventory Management

What is the Value of Censored Data? An Exact Analysis for the Data-driven Newsvendor