231 search results - page 12 / 47 » Sensitivity of trust-region algorithms to their parameters |
NECO
2010
13 years 5 months ago
2010
Most conventional Policy Gradient Reinforcement Learning (PGRL) algorithms neglect (or do not explicitly make use of) a term in the average reward gradient with respect to the pol...
FTDCS
1997
IEEE
13 years 11 months ago
1997
IEEE
This paper deals with the problem of scheduling aperiodic groups of tasks in distributed systems. It proposes two contributions, namely: i) a distributed scheduling algorithm to b...
NAACL
2003
13 years 8 months ago
2003
We investigate single-view algorithms as an alternative to multi-view algorithms for weakly supervised learning for natural language processing tasks without a natural feature spl...
MICCAI
2003
Springer
14 years 8 months ago
2003
Springer
Abstract. We present a novel technique where a medical image segmentation system is evolved using genetic programming. The evolved system was trained on just 8 images outlined by a...
WADS
2007
Springer
14 years 1 months ago
2007
Springer
Building on the work of Martinetz, Schulten and de Silva, Carlsson, we introduce a 2-parameter family of witness complexes and algorithms for constructing them. This family can be ...