536 search results - page 85 / 108 » Residual Algorithms: Reinforcement Learning with Function Ap... |
CVPR
2007
IEEE
14 years 9 months ago
2007
IEEE
The success of tensor-based subspace learning depends heavily on reducing correlations along the column vectors of the mode-k flattened matrix. In this work, we study the problem ...
AAAI
2011
12 years 7 months ago
2011
In this paper we propose differential eligibility vectors (DEV) for temporal-difference (TD) learning, a new class of eligibility vectors designed to bring out the contribution of...
TFS
2008
13 years 7 months ago
2008
Abstract--Since the fuzzy cerebellar model articulation controller (FCMAC) uses linguistic variables, it is highly intuitive and easily comprehended. Despite the FCMAC's good ...
ICMLA
2009
13 years 5 months ago
2009
This article proposes an algorithm to automatically learn useful transformations of data to improve accuracy in supervised classification tasks. These transformations take the for...
STOC
2005
ACM
14 years 8 months ago
2005
ACM
We study an extension of the "standard" learning models to settings where observing the value of an attribute has an associated cost (which might be different for differ...