4930 search results - page 109 / 986 » Learning minimal abstractions |
ECML
2004
Springer
15 years 6 months ago
2004
Springer
HEXQ is a reinforcement learning algorithm that discovers hierarchical structure automatically. The generated task hierarchy repthe problem at different levels of abstraction. In ...
ECTEL
2006
Springer
15 years 4 months ago
2006
Springer
Abstract. Attention, which intervenes at many different levels such as the perception of the environment and the allocation of cognitive resources, appears to represent one of the ...
88
Voted
ICML
2010
IEEE
14 years 10 months ago
2010
IEEE
We provide a novel view of learning an approximate model of a partially observable environment from data and present a simple implemenf the idea. The learned model abstracts away ...
90
Voted
AAAI
2008
15 years 3 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...
89
Voted
NIPS
2007
15 years 2 months ago
2007
Can we leverage learning techniques to build a fast nearest-neighbor (ANN) retrieval data structure? We present a general learning framework for the NN problem in which sample que...