Sciweavers

3084 search results - page 55 / 617
» Learning to Take Actions
Sort
View
SAC
2005
ACM
15 years 3 months ago
Reinforcement learning agents with primary knowledge designed by analytic hierarchy process
This paper presents a novel model of reinforcement learning agents. A feature of our learning agent model is to integrate analytic hierarchy process (AHP) into a standard reinforc...
Kengo Katayama, Takahiro Koshiishi, Hiroyuki Narih...
HICSS
2003
IEEE
174views Biometrics» more  HICSS 2003»
15 years 3 months ago
Linking Perception and Action in a Control Architecture for Human-Robot Domains
Human-robot interaction is a growing research domain; there are many approaches to robot design, depending on the particular aspects of interaction being focused on. In this paper...
Monica N. Nicolescu, Maja J. Mataric
CVPR
2009
IEEE
16 years 4 months ago
Max-Margin Hidden Conditional Random Fields for Human Action Recognition
We present a new method for classification with structured latent variables. Our model is formulated using the max-margin formalism in the discriminative learning literature. We...
Yang Wang 0003, Greg Mori
ICML
2005
IEEE
15 years 10 months ago
Action respecting embedding
Dimensionality reduction is the problem of finding a low-dimensional representation of highdimensional input data. This paper examines the case where additional information is kno...
Michael H. Bowling, Ali Ghodsi, Dana F. Wilkinson
ICRA
2008
IEEE
119views Robotics» more  ICRA 2008»
15 years 4 months ago
Maximum likelihood estimation of sensor and action model functions on a mobile robot
— In order for a mobile robot to accurately interpret its sensations and predict the effects of its actions, it must have accurate models of its sensors and actuators. These mode...
Daniel Stronger, Peter Stone