Sciweavers

2090 search results - page 159 / 418
» Learning with attribute costs
Sort
View
ATAL
2008
Springer
13 years 11 months ago
Learning task-specific trust decisions
We study the problem of agents locating other agents that are both capable and willing to help complete assigned tasks. An agent incurs a fixed cost for each help request it sends...
Ikpeme Erete, Erin Ferguson, Sandip Sen
AAAI
2000
13 years 10 months ago
Localizing Search in Reinforcement Learning
Reinforcement learning (RL) can be impractical for many high dimensional problems because of the computational cost of doing stochastic search in large state spaces. We propose a ...
Gregory Z. Grudic, Lyle H. Ungar
BMCBI
2007
113views more  BMCBI 2007»
13 years 9 months ago
Learning biophysically-motivated parameters for alpha helix prediction
Background: Our goal is to develop a state-of-the-art protein secondary structure predictor, with an intuitive and biophysically-motivated energy model. We treat structure predict...
Blaise Gassend, Charles W. O'Donnell, William Thie...
IJRR
2010
177views more  IJRR 2010»
13 years 7 months ago
Learning from Demonstration for Autonomous Navigation in Complex Unstructured Terrain
Rough terrain autonomous navigation continues to pose a challenge to the robotics community. Robust navigation by a mobile robot depends not only on the individual performance of ...
David Silver, J. Andrew Bagnell, Anthony Stentz
ICA
2007
Springer
14 years 1 months ago
Phase-Aware Non-negative Spectrogram Factorization
Non-negative spectrogram factorization has been proposed for single-channel source separation tasks. These methods operate on the magnitude or power spectrogram of the input mixtur...
R. Mitchell Parry, Irfan A. Essa