180 search results - page 5 / 36 » Improved bounds on the sample complexity of learning |
COLT
2010
Springer
13 years 5 months ago
2010
Springer
We present a new online learning algorithm in the selective sampling framework, where labels must be actively queried before they are revealed. We prove bounds on the regret of ou...
ATAL
2006
Springer
13 years 11 months ago
2006
Springer
Factored representations, model-based learning, and hierarchies are well-studied techniques for improving the learning efficiency of reinforcement-learning algorithms in large-sca...
COLT
2000
Springer
13 years 12 months ago
2000
Springer
We model reinforcement learning as the problem of learning to control a Partially Observable Markov Decision Process ( ¢¡¤£¦¥§ ), and focus on gradient ascent approache...
IPL
2010
13 years 6 months ago
2010
We study the problem of learning parity functions that depend on at most k variables (kparities) attribute-efficiently in the mistake-bound model. We design a simple, deterministi...
ICML
2006
IEEE
14 years 8 months ago
2006
IEEE
We state and analyze the first active learning algorithm which works in the presence of arbitrary forms of noise. The algorithm, A2 (for Agnostic Active), relies only upon the ass...