2934 search results - page 204 / 587 » Hypothesis Spaces for Learning |
170
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...
174
click to vote
ICML
2001
IEEE
16 years 7 months ago
2001
IEEE
This paper presents an active learning method that directly optimizes expected future error. This is in contrast to many other popular techniques that instead aim to reduce versio...
180
click to vote
EDUTAINMENT
2007
Springer
16 years 20 days ago
2007
Springer
Due to the high-dimensionality of motion captured data which resulted in the complexity in motion analysis, a method of motion data processing based on manifold learning was propos...
158
click to vote
ICRA
2005
IEEE
16 years 3 days ago
2005
IEEE
— This paper proposes a learning framework for a CPG-based biped locomotion controller using a policy gradient method. Our goal in this study is to develop an efficient learning...
218
click to vote
CIVR
2005
Springer
16 years 1 days ago
2005
Springer
Multiple Instance Learning (MIL) is a special kind of supervised learning problem that has been studied actively in recent years. We propose an approach based on One-Class Support ...