Learning in Structured MDPs with Convex Cost Functions: Improved Regret Bounds for Inventory Management

DOI10.1287/opre.2022.2263zbMath1494.90004arXiv1905.04337OpenAlexW2944461362MaRDI QIDQ5095166

Randy Jia, Shipra Agrawal

Publication date: 5 August 2022

Published in: Operations Research (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1905.04337

zbMATH Keywords

inventory control problemreinforcement learningregret boundscensored demandonline convex optimization

Mathematics Subject Classification ID

Convex programming (90C25) Transportation, logistics and supply chain management (90B06) Inventory, storage, reservoirs (90B05)

Related Items (1)

Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Lost-sales inventory theory: a review
• Non-Stationary Stochastic Optimization
• A note on the convexity of performance measures of M/M/c queueing systems
• Asymptotic Optimality of Order-Up-To Policies in Lost Sales Inventory Systems
• A Nonparametric Asymptotic Analysis of Inventory Planning with Censored Demand
• An Adaptive Algorithm for Finding the Optimal Base-Stock Policy in Lost Sales Inventory Systems with Censored Demand
• Old and New Methods for Lost-Sales Inventory Systems
• Optimal Server Allocation in a System of Multi-Server Stations
• Note—On the Marginal Benefit of Adding Servers to G/GI/m Queues
• Partial Monitoring—Classification, Regret Bounds, and Algorithms
• Lost-Sales Problems with Stochastic Lead Times: Convexity Results for Base-Stock Policies

This page was built for publication: Learning in Structured MDPs with Convex Cost Functions: Improved Regret Bounds for Inventory Management