On dynamic programming and statistical decision theory

DOI10.1214/AOS/1176344625zbMath0417.62002OpenAlexW2089237209MaRDI QIDQ755265

Manfred Schäl

Publication date: 1979

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

Full work available at URL: https://doi.org/10.1214/aos/1176344625

zbMATH Keywords

statistical decision theoryrisk functionBayes policiesfavourable a priori distributionsminimax policiesnon Markovian dynamic programming decision modelrenewal decision modelssequential modeltotal cost criterion

Mathematics Subject Classification ID

Dynamic programming in optimal control and differential games (49L20) Dynamic programming (90C39) Optimal stopping in statistics (62L15) Applications of Markov renewal processes (reliability, queueing networks, etc.) (60K20) General considerations in statistical decision theory (62C05)

Related Items (14)

Constrained discounted stochastic games ⋮ Vector-valued Markov decision processes and the systems of linear inequalities ⋮ On compactness of the space of policies in stochastic dynamic programming ⋮ On the expected total reward with unbounded returns for Markov decision processes ⋮ Parametric continuity in dynamic programming problems ⋮ Optimal stationary policies in the vector-valued Markov decision process ⋮ Parametric continuity in dynamic programming problems ⋮ Compactness of the space of non-randomized policies in countable-state sequential decision processes ⋮ Markov decision processes with quasi-hyperbolic discounting ⋮ Constrained discounted Markov decision processes with Borel state spaces ⋮ Semicontinuous nonstationary stochastic games. II ⋮ Constrained Markov Decision Processes with Expected Total Reward Criteria ⋮ Generalized Bandit Problems ⋮ Markov decision processes under ambiguity

This page was built for publication: On dynamic programming and statistical decision theory