1325 search results - page 76 / 265 » Algorithm Selection using Reinforcement Learning |
164
click to vote
JAIR
2007
15 years 3 months ago
2007
In this paper we present a general, flexible framework for learning mappings from images to actions by interacting with the environment. The basic idea is to introduce a feature-...
115
click to vote
ICML
2004
IEEE
16 years 4 months ago
2004
IEEE
We present a method for constructing ensembles from libraries of thousands of models. Model libraries are generated using different learning algorithms and parameter settings. For...
116
click to vote
ESANN
2008
15 years 4 months ago
2008
The aim of this paper is to enhance the performance of a reinforcement learning game agent controller, within a dynamic game environment, through the retention of learned informati...
131
click to vote
ICML
2000
IEEE
16 years 4 months ago
2000
IEEE
Landmarking is a novel approach to describing tasks in meta-learning. Previous approaches to meta-learning mostly considered only statistics-inspired measures of the data as a sou...
114
click to vote
ICML
2002
IEEE
16 years 4 months ago
2002
IEEE
Searching the space of policies directly for the optimal policy has been one popular method for solving partially observable reinforcement learning problems. Typically, with each ...