Sciweavers

1674 search results - page 137 / 335
» Learning Actions From the Web
Sort
View
ICRA
1995
IEEE
79views Robotics» more  ICRA 1995»
15 years 7 months ago
Learning to predict Resistive Forces During Robotic Excavation
— Few robot tasks require as forceful an interaction with the world as excavation. In order to effectively plan its actions, our robot excavator requires a method that allows it ...
Sanjiv Singh
BC
2002
91views more  BC 2002»
15 years 3 months ago
Mathematical formulations of Hebbian learning
Several formulations of correlation-based Hebbian learning are reviewed. On the presynaptic side, activity is described either by a firing rate or by presynaptic spike arrival. The...
Wulfram Gerstner, Werner M. Kistler
JMLR
2010
163views more  JMLR 2010»
14 years 10 months ago
Active Sequential Learning with Tactile Feedback
We consider the problem of tactile discrimination, with the goal of estimating an underlying state parameter in a sequential setting. If the data is continuous and highdimensional...
Hannes Saal, Jo-Anne Ting, Sethu Vijayakumar
ECML
2005
Springer
15 years 9 months ago
Using Rewards for Belief State Updates in Partially Observable Markov Decision Processes
Partially Observable Markov Decision Processes (POMDP) provide a standard framework for sequential decision making in stochastic environments. In this setting, an agent takes actio...
Masoumeh T. Izadi, Doina Precup
AAAI
1998
15 years 5 months ago
Bayesian Q-Learning
A central problem in learning in complex environmentsis balancing exploration of untested actions against exploitation of actions that are known to be good. The benefit of explora...
Richard Dearden, Nir Friedman, Stuart J. Russell