Stationary Policies in Dynamic Programming Models Under Compactness Assumptions

DOI10.1287/MOOR.8.3.366zbMath0533.90093OpenAlexW2018190357MaRDI QIDQ3316991

Manfred Schäl

Publication date: 1983

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

Full work available at URL: https://doi.org/10.1287/moor.8.3.366

zbMATH Keywords

convergence conditionexpected total rewardsstationary decision model

Mathematics Subject Classification ID

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

Related Items (11)

The existence of good Markov strategies for decision processes with general payoffs ⋮ Non-randomized strategies in stochastic decision processes ⋮ Finite state dynamic programming with the total reward criterion ⋮ Optimizing high-dimensional stochastic forestry \textit{via} reinforcement learning ⋮ A Convex Programming Approach for Discrete-Time Markov Decision Processes under the Expected Total Reward Criterion ⋮ Semi-infinite Markov decision processes ⋮ Maximizing the probability of visiting a set infinitely often for a countable state space Markov decision process ⋮ Markov decision processes with risk-sensitive criteria: an overview ⋮ Maximizing the probability of visiting a set infinitely often for a Markov decision process with Borel state and action spaces ⋮ On Convergence of Value Iteration for a Class of Total Cost Markov Decision Processes ⋮ Stationary policies and Markov policies in Borel dynamic programming

This page was built for publication: Stationary Policies in Dynamic Programming Models Under Compactness Assumptions