12 search results - page 1 / 3 » Topmoumoute Online Natural Gradient Algorithm |
NIPS
2007
13 years 11 months ago
2007
Guided by the goal of obtaining an optimization algorithm that is both fast and yields good generalization, we study the descent direction maximizing the decrease in generalizatio...
NIPS
2007
13 years 11 months ago
2007
We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning m...
JMLR
2010
13 years 4 months ago
2010
In this paper, we propose a novel adaptive step-size approach for policy gradient reinforcement learning. A new metric is defined for policy gradients that measures the effect of ...
ACL
2009
13 years 7 months ago
2009
Stochastic gradient descent (SGD) uses approximate gradients estimated from subsets of the training data and updates the parameters in an online fashion. This learning framework i...
JMLR
2008
13 years 10 months ago
2008
Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of...