Abstract | ||
---|---|---|
We analyze a simple, Bellman-error-based approach to generating basis functions for value-function 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. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1145/1273496.1273589 | ICML |
Keywords | Field | DocType |
analyzing feature generation,sample problem,approximation error bound,basis function,value-function approximation,bellman-error-based approach,orthogonal basis function,approximation error | Applied mathematics,Computer science,Discrete dipole approximation codes,Orthogonal basis,Artificial intelligence,Basis function,Spouge's approximation,Approximation algorithm,Mathematical optimization,Pattern recognition,Minimax approximation algorithm,Approximation error,Small-angle approximation | Conference |
Citations | PageRank | References |
59 | 3.22 | 11 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ronald Parr | 1 | 2428 | 186.85 |
Christopher Painter-Wakefield | 2 | 170 | 7.96 |
Lihong Li | 3 | 2390 | 128.53 |
Michael L. Littman | 4 | 9798 | 961.84 |