Performance guarantees for empirical Markov decision processes with applications to multiperiod inventory models

DOI10.1287/OPRE.1120.1090zbMATH Open1263.90121OpenAlexW2140190730MaRDI QIDQ4904590FDOQ4904590

Authors: William L. Cooper, Bharath Rangarajan 

Publication date: 30 January 2013

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

Full work available at URL: https://semanticscholar.org/paper/9675808fd9c15a25e0d16d03711e86e9aa63cb99

Recommendations

• On the convergence of optimal actions for Markov decision processes and the optimality of \((s,S)\) inventory policies
• Approximation of average cost Markov decision processes using empirical distributions and concentration inequalities
• Provably Near-Optimal Sampling-Based Policies for Stochastic Inventory Control Models
• Robust Markov Decision Processes with Data-Driven, Distance-Based Ambiguity Sets
• Robust Markov Decision Processes

zbMATH Keywords

estimationinventory/production

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Cited In (4)

• Some limit properties of Markov chains induced by recursive stochastic algorithms
• Dynamic Inventory Control with Fixed Setup Costs and Unknown Discrete Demand Distribution
• \((s,S)\) inventory systems with correlated demands
• Empirical dynamic programming

This page was built for publication: Performance guarantees for empirical Markov decision processes with applications to multiperiod inventory models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4904590)