139 search results - page 6 / 28 » Model-based function approximation in reinforcement learning |
113
Voted
AAAI
2011
13 years 9 months ago
2011
We describe the Fourier Basis, a linear value function approximation scheme based on the Fourier Series. We empirically evaluate its properties, and demonstrate that it performs w...
106
click to vote
ICML
2006
IEEE
2006
IEEE
Automatic basis function construction for approximate dynamic programming and reinforcement learning
15 years 3 months ago
We address the problem of automatically constructing basis functions for linear approximation of the value function of a Markov Decision Process (MDP). Our work builds on results ...
ATAL
2009
Springer
15 years 4 months ago
2009
Springer
AMAI
2004
Springer
15 years 2 months ago
2004
Springer
ICINCO
2008
14 years 11 months ago
2008