Estimate and approximate policy iteration algorithm for discounted Markov decision models with bounded costs and Borel spaces
From MaRDI portal
Publication:3119642
DOI10.3233/RDA-160116zbMath1409.90218WikidataQ114943784 ScholiaQ114943784MaRDI QIDQ3119642
Ma. Teresa Robles Alcaraz, Óscar Vega-Amaya, J. Adolfo Minjárez-Sosa
Publication date: 12 March 2019
Published in: Risk and Decision Analysis (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.3233/rda-160116
90C40: Markov and semi-Markov decision processes
Related Items
A perturbation approach to approximate value iteration for average cost Markov decision processes with Borel spaces and bounded costs, Time-varying Markov decision processes with state-action-dependent discount factors and unbounded costs, Approximation of discounted minimax Markov control problems and zero-sum Markov games using Hausdorff and Wasserstein distances