Sciweavers

3274 search results - page 346 / 655
» Using Learning in a Control Agent
Sort
View
AAAI
2006
15 years 8 months ago
Decision Tree Methods for Finding Reusable MDP Homomorphisms
straction is a useful tool for agents interacting with environments. Good state abstractions are compact, reuseable, and easy to learn from sample data. This paper and extends two...
Alicia P. Wolfe, Andrew G. Barto
COGSCI
2007
87views more  COGSCI 2007»
15 years 6 months ago
Explaining Color Term Typology With an Evolutionary Model
An expression-induction model was used to simulate the evolution of basic color terms to test Berlin and Kay’s (1969) hypothesis that the typological patterns observed in basic ...
Mike Dowman
200
Voted
JMLR
2008
151views more  JMLR 2008»
15 years 6 months ago
Learning to Combine Motor Primitives Via Greedy Additive Regression
The computational complexities arising in motor control can be ameliorated through the use of a library of motor synergies. We present a new model, referred to as the Greedy Addit...
Manu Chhabra, Robert A. Jacobs
ICCV
2003
IEEE
16 years 8 months ago
Controlling Model Complexity in Flow Estimation
This paper describes a novel application of Statistical Learning Theory (SLT) to control model complexity in flow estimation. SLT provides analytical generalization bounds suitabl...
Zoran Duric, Fayin Li, Harry Wechsler, Vladimir Ch...
ICRA
2007
IEEE
155views Robotics» more  ICRA 2007»
16 years 1 months ago
Value Function Approximation on Non-Linear Manifolds for Robot Motor Control
— The least squares approach works efficiently in value function approximation, given appropriate basis functions. Because of its smoothness, the Gaussian kernel is a popular an...
Masashi Sugiyama, Hirotaka Hachiya, Christopher To...