121 search results - page 17 / 25 » Toward Off-Policy Learning Control with Function Approximati... |
GECCO
2008
Springer
13 years 10 months ago
2008
Springer
While John Holland has always envisioned learning classifier systems (LCSs) as cognitive systems, most work on LCSs has focused on classification, datamining, and function appro...
ECML
2006
Springer
14 years 23 days ago
2006
Springer
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
ICML
2000
IEEE
14 years 10 months ago
2000
IEEE
This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled ??? ?s. We introduce ??? ?, a...
NIPS
2004
13 years 10 months ago
2004
Log-concavity is an important property in the context of optimization, Laplace approximation, and sampling; Bayesian methods based on Gaussian process priors have become quite pop...
FLAIRS
2003
13 years 10 months ago
2003
Researchers studying Evolutionary Algorithms and their applications have always been confronted with the sample complexity problem. The relationship between population size and gl...