3411 search results - page 241 / 683 » Adaptive Transfer Learning |
133
click to vote
COLT
2005
Springer
15 years 10 months ago
2005
Springer
We start by showing that in an active learning setting, the Perceptron algorithm needs Ω( 1 ε2 ) labels to learn linear separators within generalization error ε. We then prese...
129
click to vote
FORMATS
2004
Springer
15 years 10 months ago
2004
Springer
Abstract. We extend Angluin’s algorithm for on-line learning of regular languages to the setting of timed systems. We consider systems that can be described by a class of determi...
134
click to vote
KES
2004
Springer
15 years 10 months ago
2004
Springer
This paper presents a novel method for on-line coordination in multiagent reinforcement learning systems. In this method a reinforcement-learning agent learns to select its action ...
131
click to vote
ATAL
2006
Springer
15 years 8 months ago
2006
Springer
RVRL (Rule Value Reinforcement Learning) is a new algorithm which extends an existing learning framework that models the environment of a situated agent using a probabilistic rule...
125
click to vote
AAAI
2008
15 years 6 months ago
2008
For many machine learning solutions to complex applications, there are significant performance advantages to decomposing the overall task into several simpler sequential stages, c...