65 search results - page 4 / 13 » Gradient Descent for General Reinforcement Learning |
JMLR
2010
13 years 4 months ago
2010
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
ICIP
2008
IEEE
14 years 11 months ago
2008
IEEE
Semi-supervised image segmentation is an important issue in many image processing applications, and has been a popular research area recently, the most popular are graph-based met...
ICML
2009
IEEE
14 years 10 months ago
2009
IEEE
In this paper we introduce the first algorithms for efficiently learning a simulation policy for Monte-Carlo search. Our main idea is to optimise the balance of a simulation polic...
ICML
2008
IEEE
14 years 10 months ago
2008
IEEE
We show how the regularizer of Transductive Support Vector Machines (TSVM) can be trained by stochastic gradient descent for linear models and multi-layer architectures. The resul...
ICML
2003
IEEE
14 years 10 months ago
2003
IEEE
In Reinforcement Learning (RL) there has been some experimental evidence that the residual gradient algorithm converges slower than the TD(0) algorithm. In this paper, we use the ...