On the Asymptotic Optimality of Finite Approximations to Markov Decision Processes with Borel Spaces

DOI10.1287/moor.2016.0832zbMath1417.93337arXiv1503.02244OpenAlexW2964034900MaRDI QIDQ4595952

Naci Saldi, Serdar Yüksel, Tamás Linder

Publication date: 7 December 2017

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

Full work available at URL: https://arxiv.org/abs/1503.02244

zbMATH Keywords

Markov decision processesstochastic controlquantizationfinite state approximation

Mathematics Subject Classification ID

Dynamic programming (90C39) Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40)

Related Items (12)

A convex optimization approach to dynamic programming in continuous state and action spaces ⋮ Dual Ascent and Primal-Dual Algorithms for Infinite-Horizon Nonstationary Markov Decision Processes ⋮ Continuity of cost in Borkar control topology and implications on discrete space and time approximations for controlled diffusions under several criteria ⋮ Robustness to Incorrect System Models in Stochastic Control ⋮ Robustness to Approximations and Model Learning in MDPs and POMDPs ⋮ Unnamed Item ⋮ Dual-based methods for solving infinite-horizon nonstationary deterministic dynamic programs ⋮ Weak Feller property of non-linear filters ⋮ Robust optimal control using conditional risk mappings in infinite horizon ⋮ A perturbation approach to approximate value iteration for average cost Markov decision processes with Borel spaces and bounded costs ⋮ A Simplex Method for Countably Infinite Linear Programs ⋮ A stability result for linear Markovian stochastic optimization problems

This page was built for publication: On the Asymptotic Optimality of Finite Approximations to Markov Decision Processes with Borel Spaces