Partially observed Markov decision process multiarmed bandits-structural results

DOI10.1287/MOOR.1080.0371MaRDI QIDQ3169035zbMATH OpenOpenAlexFDO

Authors Vikram Krishnamurthy, B. Wahlberg

Publication date 27 April 2011

Published in Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1287/moor.1080.0371

zbMATH Keywords

likelihood ratio orderingmonotone policiesmultiarmed banditsopportunistic schedulingpartially observed Markov decision processstochastic approximation algorithm

Mathematics Subject Classification ID

Deterministic scheduling theory in operations research (90B35) Markov and semi-Markov decision processes (90C40) Approximation methods and heuristics in mathematical programming (90C59)

Recommendations

• The Multi-Armed Bandit Problem: Decomposition and Computation
• On the Gittins index for multiarmed bandits
• Solution Procedures for Partially Observed Markov Decision Processes
• A survey of solution techniques for the partially observed Markov decision process
• Optimal Threshold Policies for Multivariate Stopping-Time POMDPs

Cited in

(6)

• Ambiguous partially observable Markov decision processes: structural results and applications
• Monotonicity properties for two-action partially observable Markov decision processes on partially ordered spaces
• Optimal Threshold Policies for Multivariate Stopping-Time POMDPs
• A Structured Multiarmed Bandit Problem and the Greedy Policy
• Game of thrones: fully distributed learning for multiplayer bandits
• Off-policy evaluation in partially observed Markov decision processes under sequential ignorability

Describes a project that uses

Uses Software

• POMDPS

This page was built for publication: Partially observed Markov decision process multiarmed bandits-structural results

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3169035)