2285 search results - page 27 / 457 » Active Imitation Learning |
IJCNN
2006
IEEE
14 years 1 months ago
2006
IEEE
Abstract— One of the major challenges in both action generation for robotics and in the understanding of human motor control is to learn the “building blocks of movement genera...
Publication
We generalise the problem of inverse reinforcement learning to multiple tasks, from multiple demonstrations. Each one may represent one expert trying to solve a different task, or ...
COLT
2007
Springer
14 years 1 months ago
2007
Springer
This paper analyzes the potential advantages and theoretical challenges of “active learning” algorithms. Active learning involves sequential sampling procedures that use infor...
ICPR
2004
IEEE
14 years 8 months ago
2004
IEEE
In an experiment with a soccer playing robot, periodic temporally-constrained nonlinear principal component neural networks (NLPCNNs) are shown to characterize humanoid motion eff...
IAT
2009
IEEE
14 years 2 months ago
2009
IEEE
—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 ...