Linear programming formulation for non-stationary, finite-horizon Markov decision process models

DOI10.1016/j.orl.2017.09.001zbMath1409.90215OpenAlexW2755855309MaRDI QIDQ1728357

Jeffrey P. Kharoufeh, Arnab Bhattacharya

Publication date: 22 February 2019

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

Full work available at URL: https://doi.org/10.1016/j.orl.2017.09.001

zbMATH Keywords

linear programmingnon-stationary MDP model

Mathematics Subject Classification ID

Linear programming (90C05) Markov and semi-Markov decision processes (90C40)

Related Items (1)

Poisoning finite-horizon Markov decision processes at design time

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A new polynomial-time algorithm for linear programming
• \({\mathcal Q}\)-learning
• An Approximate Dynamic Programming Algorithm for Monotone Value Functions
• Approximate Dynamic Programming
• A Fast Algorithm for Linear Programming
• Dynamic Bid Prices in Revenue Management
• Dynamic Multipriority Patient Scheduling for a Diagnostic Resource
• The Linear Programming Approach to Approximate Dynamic Programming
• The Complexity of Markov Decision Processes
• Linear Programming and Markov Decision Chains
• On the Complexity of the Policy Improvement Algorithm for Markov Decision Processes
• A Distributed Decision-Making Structure for Dynamic Resource Allocation Using Nonlinear Functional Approximations
• On Constraint Sampling in the Linear Programming Approach to Approximate Dynamic Programming

This page was built for publication: Linear programming formulation for non-stationary, finite-horizon Markov decision process models