7928 search results - page 275 / 1586 » Human-Like Learning Methods for a |
161
click to vote
ICML
2004
IEEE
16 years 7 months ago
2004
IEEE
lative Novelty to Identify Useful Temporal Abstractions in Reinforcement Learning ?Ozg?ur S?im?sek ozgur@cs.umass.edu Andrew G. Barto barto@cs.umass.edu Department of Computer Scie...
176
click to vote
ICML
2003
IEEE
16 years 7 months ago
2003
IEEE
We present a new method for transductive learning, which can be seen as a transductive version of the k nearest-neighbor classifier. Unlike for many other transductive learning me...
164
click to vote
ICML
2001
IEEE
16 years 7 months ago
2001
IEEE
Hierarchical reinforcement learning (RL) is a general framework which studies how to exploit the structure of actions and tasks to accelerate policy learning in large domains. Pri...
141
click to vote
MLCW
2005
Springer
15 years 11 months ago
2005
Springer
In this paper we present lessons learned in the Evaluating Predictive Uncertainty Challenge. We describe the methods we used in regression challenges, including our winning method ...
185
click to vote
ECML
2007
Springer
15 years 10 months ago
2007
Springer
Abstract. Ensemble methods are popular learning methods that usually increase the predictive accuracy of a classifier though at the cost of interpretability and insight in the deci...