NA
2008
13 years 4 months ago
2008
Another hybrid conjugate gradient algorithm is subject to analysis. The parameter k is computed as a convex combination of HS k (Hestenes-Stiefel) and DY k (Dai-Yuan) algorithms, i...
JMLR
2006
13 years 4 months ago
2006
Policy search is a method for approximately solving an optimal control problem by performing a parametric optimization search in a given class of parameterized policies. In order ...
JMLR
2006
13 years 4 months ago
2006
We introduce an algorithm that learns gradients from samples in the supervised learning framework. An error analysis is given for the convergence of the gradient estimated by the ...
UAI
2001
13 years 5 months ago
2001
There exist a number of reinforcement learning algorithms which learn by climbing the gradient of expected reward. Their long-run convergence has been proved, even in partially ob...
IJCAI
2003
13 years 5 months ago
2003
We investigate the problem of non-covariant behavior of policy gradient reinforcement learning algorithms. The policy gradient approach is amenable to analysis by information geom...
NIPS
2001
13 years 5 months ago
2001
Policy gradient methods for reinforcement learning avoid some of the undesirable properties of the value function approaches, such as policy degradation (Baxter and Bartlett, 2001...
GRAPHICSINTERFACE
2003
13 years 5 months ago
2003
To apply empty space skipping in texture-based volume rendering, we partition the texture space with a box-growing algorithm. Each sub-texture comprises of neighboring voxels with...
NIPS
2007
13 years 6 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...
ECCV
2008
Springer
13 years 6 months ago
2008
Springer
We analyze the problem of reconstructing a 2D function that approximates a set of desired gradients and a data term. The combined data and gradient terms enable operations like mod...
DAS
2008
Springer
13 years 6 months ago
2008
Springer
The use of gradients in text images is nowadays quite frequent. Existing segmentation methods encounter serious problems when it comes to modern text images where gradients might ...