Sufficient Classes of Strategies in Discrete Dynamic Programming I: Decomposition of Randomized Strategies and Embedded Models

DOI10.1137/1131088zbMath0641.90086OpenAlexW2079806887MaRDI QIDQ3783096

Eugene A. Feinberg

Publication date: 1987

Published in: Theory of Probability & Its Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/1131088

zbMATH Keywords

infinite time intervalstationary controlsnonstationary strategies\(\epsilon \) \(\ell \)-optimal strategiesF- strategies

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Related Items (5)

Solving average cost Markov decision processes by means of a two-phase time aggregation algorithm ⋮ Non-randomized strategies in stochastic decision processes ⋮ Time aggregated Markov decision processes via standard dynamic programming ⋮ Exact finite approximations of average-cost countable Markov decision processes ⋮ MDPs with setwise continuous transition probabilities

This page was built for publication: Sufficient Classes of Strategies in Discrete Dynamic Programming I: Decomposition of Randomized Strategies and Embedded Models