On the construction of \(\epsilon\)-optimal strategies in partially observed MDPs

DOI10.1007/BF02055576zbMath0717.90085OpenAlexW2035702947MaRDI QIDQ2638958

Wolfgang J. Runggaldier

Publication date: 1991

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

Full work available at URL: https://doi.org/10.1007/bf02055576

zbMATH Keywords

surveyapproximation techniques\(\epsilon \) -optimal strategiespartially observable MDPs

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Research exposition (monographs, survey articles) pertaining to operations research and mathematical programming (90-02) Computational methods for problems pertaining to operations research and mathematical programming (90-08)

Related Items (1)

Asymptotically optimal Bayesian sequential change detection and identification rules

Cites Work

• Unnamed Item
• Probability methods for approximations in stochastic control and for elliptic equations
• An approximation method for stochastic control problems with partial observation of the state - a method for constructing \(\in\)-optimal controls
• Approximations for discrete-time adaptive control: Construction of \(\varepsilon\)-optimal controls
• On Transforming a Certain Class of Stochastic Processes by Absolutely Continuous Substitution of Measures
• State of the Art—A Survey of Partially Observable Markov Decision Processes: Theory, Models, and Algorithms
• On the construction of nearly optimal strategies for a general problem of control of partially observed diffusions
• Markovian Decision Processes with Probabilistic Observation of States
• Convergence of discretization procedures in dynamic programming
• The Optimal Control of Partially Observable Markov Processes over the Infinite Horizon: Discounted Costs
• Approximations of Dynamic Programs, I
• The Optimal Control of Partially Observable Markov Processes over a Finite Horizon
• An Approach to Discrete-Time Stochastic Control Problems under Partial Observation
• Solution Procedures for Partially Observed Markov Decision Processes
• Numerical Methods for Stochastic Control Problems in Continuous Time

This page was built for publication: On the construction of \(\epsilon\)-optimal strategies in partially observed MDPs