87 search results - page 2 / 18 » Hybrid Least-Squares Algorithms for Approximate Policy Evalu... |
NIPS
2001
13 years 6 months ago
2001
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
VTC
2007
IEEE
13 years 11 months ago
2007
IEEE
Abstract— An adaptive handover algorithm for wireless comn systems is addressed in this extended abstract. Moving from the Generalized Extended Least Square handover algorithm in...
ICRA
2003
IEEE
13 years 10 months ago
2003
IEEE
— One of the most difficult aspects of dealing with illumination effects in computer vision is accounting for specularity in the images of real objects. The specular regions in ...
ICMLA
2008
13 years 6 months ago
2008
In reinforcement learning, it is a common practice to map the state(-action) space to a different one using basis functions. This transformation aims to represent the input data i...
ISSAC
2007
Springer
13 years 11 months ago
2007
Springer
Approximate symbolic computation problems can be formulated as constrained or unconstrained optimization problems, for example: GCD [3, 8, 12, 13, 23], factorization [5, 10], and ...