On the Asymptotic Optimality of Finite Approximations to Markov Decision Processes with Borel Spaces
From MaRDI portal
Publication:4595952
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
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
