Sciweavers

495 search results - page 7 / 99
» Learning to generalize for complex selection tasks
Sort
View
WEBI
2010
Springer
13 years 4 months ago
Learning Task Specific Web Services Compositions with Loops and Conditional Branches from Example Executions
Majority of the existing approaches to service composition, including the widely popular planning based techniques, are not able to automatically compose practical workflows that ...
Harini Veeraraghavan, Roman Vaculín, Manuel...
ATAL
2009
Springer
14 years 1 months ago
Adaptive learning in evolving task allocation networks
In this paper, we study multi-agent economic systems using a recent approach to economic modeling called Agent-based Computational Economics (ACE): the application of the Complex ...
Tomas Klos, Bart Nooteboom
ICML
2006
IEEE
14 years 7 months ago
Learning hierarchical task networks by observation
Knowledge-based planning methods offer benefits over classical techniques, but they are time consuming and costly to construct. There has been research on learning plan knowledge ...
Negin Nejati, Pat Langley, Tolga Könik
CVPR
2005
IEEE
14 years 8 months ago
Cross-Generalization: Learning Novel Classes from a Single Example by Feature Replacement
We develop an object classification method that can learn a novel class from a single training example. In this method, experience with already learned classes is used to facilita...
Evgeniy Bart, Shimon Ullman
ECML
2006
Springer
13 years 10 months ago
Task-Driven Discretization of the Joint Space of Visual Percepts and Continuous Actions
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
Sébastien Jodogne, Justus H. Piater