Sciweavers

74 search results - page 4 / 15
» Imitation learning with generalized task descriptions
Sort
View
IAT
2009
IEEE
14 years 2 months ago
Agent-Based Security System for User Verification
—We present a security system consisting of an arbitrary number of entries, sensors and agents. The intelligent integrated system is based on user modeling, i.e. models of their ...
Erik Dovgan, Bostjan Kaluza, Tea Tusar, Matjaz Gam...
NIPS
2008
13 years 9 months ago
Policy Search for Motor Primitives in Robotics
Many motor skills in humanoid robotics can be learned using parametrized motor primitives as done in imitation learning. However, most interesting motor learning problems are high...
Jens Kober, Jan Peters
IUI
2005
ACM
14 years 1 months ago
Task learning by instruction in tailor
In order for intelligent systems to be applicable in a wide range of situations, end users must be able to modify their task descriptions. We introduce Tailor, a system that allow...
Jim Blythe
MLDM
2009
Springer
14 years 2 months ago
An Evidence-Driven Probabilistic Inference Framework for Semantic Image Understanding
This work presents an image analysis framework driven by emerging evidence and constrained by the semantics expressed in an ontology. Human perception, apart from visual stimulus a...
Spiros Nikolopoulos, Georgios Th. Papadopoulos, Io...
ATAL
2006
Springer
13 years 11 months ago
Learning the required number of agents for complex tasks
Coordinating agents in a complex environment is a hard problem, but it can become even harder when certain characteristics of the tasks, like the required number of agents, are un...
Sébastien Paquet, Brahim Chaib-draa