Sciweavers

Share
ICML
2007
IEEE

Analyzing feature generation for value-function approximation

10 years 3 months ago
Analyzing feature generation for value-function approximation
We analyze a simple, Bellman-error-based approach to generating basis functions for valuefunction approximation. We show that it generates orthogonal basis functions that provably tighten approximation error bounds. We also illustrate the use of this approach in the presence of noise on some sample problems.
Ronald Parr, Christopher Painter-Wakefield, Lihong
Added 17 Nov 2009
Updated 17 Nov 2009
Type Conference
Year 2007
Where ICML
Authors Ronald Parr, Christopher Painter-Wakefield, Lihong Li, Michael L. Littman
Comments (0)
books