Error Bounds for Approximations from Projected Linear Equations
From MaRDI portal
Publication:3169095
DOI10.1287/moor.1100.0441zbMath1218.90211OpenAlexW2140778663MaRDI QIDQ3169095
Dimitri P. Bertsekas, Huizhen Yu
Publication date: 27 April 2011
Published in: Mathematics of Operations Research (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1287/moor.1100.0441
dynamic programmingerror boundsGalerkin methodstemporal difference methodsfunction approximationprojected linear equations
Approximation methods and heuristics in mathematical programming (90C59) Markov and semi-Markov decision processes (90C40) Approximation by arbitrary linear expressions (41A45)
Related Items
Approximate policy iteration: a survey and some new methods, On Generalized Bellman Equations and Temporal-Difference Learning, Proximal algorithms and temporal difference methods for solving fixed point problems, Off-policy temporal difference learning with distribution adaptation in fast mixing chains