2 search results - page 1 / 1 » Proto-value functions: developmental reinforcement learning |
AAAI
2011
12 years 4 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...
ICML
2005
IEEE
14 years 5 months ago
2005
IEEE
This paper presents a novel framework called proto-reinforcement learning (PRL), based on a mathematical model of a proto-value function: these are task-independent basis function...