995 search results - page 17 / 199 » Learning Useful Horn Approximations |
ICML
2007
IEEE
14 years 10 months ago
2007
IEEE
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...
FUZZIEEE
2007
IEEE
14 years 4 months ago
2007
IEEE
— Reinforcement learning (RL) is a learning control paradigm that provides well-understood algorithms with good convergence and consistency properties. Unfortunately, these algor...
UAI
2004
13 years 11 months ago
2004
Bayesian learning in undirected graphical models--computing posterior distributions over parameters and predictive quantities-is exceptionally difficult. We conjecture that for ge...
ICML
2004
IEEE
14 years 10 months ago
2004
IEEE
Synchronous reinforcement learning (RL) algorithms with linear function approximation are representable as inhomogeneous matrix iterations of a special form (Schoknecht & Merk...
ICML
2004
IEEE
14 years 10 months ago
2004
IEEE
The multiple-instance learning (MIL) model has been very successful in application areas such as drug discovery and content-based imageretrieval. Recently, a generalization of thi...