Approximate Fixed Point Iteration with an Application to Infinite Horizon Markov Decision Processes

DOI10.1137/S0363012904441520zbMath1175.65003MaRDI QIDQ3399246

Anthony Almudevar

Publication date: 29 September 2009

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

zbMATH Keywords

dynamic programmingfixed pointMarkov decision processescontraction mappings

Mathematics Subject Classification ID

Monte Carlo methods (65C05) Stochastic learning and adaptive control (93E35) Markov and semi-Markov decision processes (90C40)

Related Items (5)

A perturbation approach to a class of discounted approximate value iteration algorithms with Borel spaces ⋮ A stochastic contraction mapping theorem ⋮ Empirical Dynamic Programming ⋮ A perturbation approach to approximate value iteration for average cost Markov decision processes with Borel spaces and bounded costs ⋮ Accelerating the convergence of value iteration by using partial transition functions

This page was built for publication: Approximate Fixed Point Iteration with an Application to Infinite Horizon Markov Decision Processes