Blackwell optimality in Markov decision processes with partial observation.

DOI10.1214/aos/1031689022zbMath1103.90402OpenAlexW2018761851MaRDI QIDQ1848970

Nicolas Vieille, Dinah Rosenberg, Eilon Solan

Publication date: 14 November 2002

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://projecteuclid.org/euclid.aos/1031689022

zbMATH Keywords

Blackwell optimalitypartial observationMarkov Decision Process

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (16)

Zero-sum repeated games: counterexamples to the existence of the asymptotic value and the conjecture \({\max}{\min}=\lim v_{n}\) ⋮ Finite-Memory Strategies in POMDPs with Long-Run Average Objectives ⋮ Unraveling in a repeated moral hazard model with multiple agents ⋮ Randomization and simplification in dynamic decision-making. ⋮ An axiomatic approach to Markov decision processes ⋮ Existence of the uniform value in zero-sum repeated games with a more informed controller ⋮ Stochastic Games ⋮ Regularity of dynamic opinion games ⋮ Periodic stopping games ⋮ Repeated games with public uncertain duration process ⋮ Zero-sum repeated games: recent advances and new links with differential games ⋮ Strong Uniform Value in Gambling Houses and Partially Observable Markov Decision Processes ⋮ A Tauberian Theorem for Nonexpansive Operators and Applications to Zero-Sum Stochastic Games ⋮ History-dependent Evaluations in Partially Observable Markov Decision Process ⋮ Commutative Stochastic Games ⋮ On values of repeated games with signals

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The economics of orchards: An exercise in point-input, flow-output capital theory
• Incomplete information in Markovian decision models
• A Partially Observable Model of Decision Making by Fishermen
• State of the Art—A Survey of Partially Observable Markov Decision Processes: Theory, Models, and Algorithms
• A Uniform Tauberian Theorem in Dynamic Programming
• Reduction of a Controlled Markov Model with Incomplete Data to a Problem with Complete Information in the Case of Borel State and Control Space
• Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
• Discrete Dynamic Programming
• Discrete-Time Markovian Decision Processes with Incomplete State Observation
• Continuous interpolation of solutions of Lipschitz inclusions

This page was built for publication: Blackwell optimality in Markov decision processes with partial observation.