Myopic Bounds for Optimal Policy of POMDPs: An Extension of Lovejoy’s Structural Results

DOI10.1287/opre.2014.1332zbMath1327.90368arXiv1404.3328OpenAlexW2139555052MaRDI QIDQ3453342

Vikram Krishnamurthy, Udit Pareek

Publication date: 20 November 2015

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

Full work available at URL: https://arxiv.org/abs/1404.3328

zbMATH Keywords

POMDPstructural resultlikelihood ratio dominancemyopic policy upper and lower bounds

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (1)

Multiple stopping time POMDPs: structural results \& application in interactive advertising on social media

Cites Work

• Planning and acting in partially observable stochastic domains
• Classes of orderings of measures and related correlation inequalities. I. Multivariate totally positive distributions
• The Complexity of Markov Decision Processes
• Some Monotonicity Results for Partially Observed Markov Decision Processes
• Structural results for partially observed control models
• Monotonicity and bounds for convex stochastic control models
• Structured Threshold Policies for Dynamic Sensor Scheduling—A Partially Observed Markov Decision Process Approach
• An Adaptive Linear Approximation Algorithm for Copositive Programs
• How to Schedule Measurements of a Noisy Markov Chain in Decision Making?

This page was built for publication: Myopic Bounds for Optimal Policy of POMDPs: An Extension of Lovejoy’s Structural Results