Sciweavers

1674 search results - page 55 / 335
» Learning Actions From the Web
Sort
View
101
Voted
ICML
2007
IEEE
16 years 2 months ago
Constructing basis functions from directed graphs for value function approximation
Basis functions derived from an undirected graph connecting nearby samples from a Markov decision process (MDP) have proven useful for approximating value functions. The success o...
Jeffrey Johns, Sridhar Mahadevan
ECAI
2004
Springer
15 years 7 months ago
Active Learning for Robot Manipulation
Abstract— Learning techniques in robotic grasping applications have usually been concerned with the way a hand approaches to an object, or with improving the motor control of man...
Antonio Morales, Eris Chinellato, Andrew H. Fagg, ...
108
Voted
ECML
1998
Springer
15 years 6 months ago
First-Order Learning for Web Mining
We present compelling evidence that the World Wide Web is a domain in which applications can benefit from using first-order learning methods, since the graph structure inherent in ...
Mark Craven, Seán Slattery, Kamal Nigam
IWINAC
2007
Springer
15 years 8 months ago
Evolving Robot Behaviour at Micro (Molecular) and Macro (Molar) Action Level
We investigate how it is possible to shape robot behaviour adopting a molecular or molar point of view. These two ways to approach the issue are inspired by Learning Psychology, wh...
Michela Ponticorvo, Orazio Miglino
CORR
2007
Springer
73views Education» more  CORR 2007»
15 years 1 months ago
Universal Reinforcement Learning
—We consider an agent interacting with an unmodeled environment. At each time, the agent makes an observation, takes an action, and incurs a cost. Its actions can influence futu...
Vivek F. Farias, Ciamac Cyrus Moallemi, Tsachy Wei...