Sciweavers

3084 search results - page 23 / 617
» Learning to Take Actions
Sort
View
IROS
2007
IEEE
123views Robotics» more  IROS 2007»
14 years 1 months ago
Reinforcement learning in multi-dimensional state-action space using random rectangular coarse coding and Gibbs sampling
: This paper presents a coarse coding technique and an action selection scheme for reinforcement learning (RL) in multi-dimensional and continuous state-action spaces following con...
Kimura Kimura
ICML
1998
IEEE
14 years 8 months ago
Intra-Option Learning about Temporally Abstract Actions
tion Learning about Temporally Abstract Actions Richard S. Sutton Department of Computer Science University of Massachusetts Amherst, MA 01003-4610 rich@cs.umass.edu Doina Precup D...
Richard S. Sutton, Doina Precup, Satinder P. Singh
ICDE
2006
IEEE
152views Database» more  ICDE 2006»
14 years 8 months ago
Mining Actionable Patterns by Role Models
Data mining promises to discover valid and potentially useful patterns in data. Often, discovered patterns are not useful to the user. "Actionability" addresses this pro...
Ke Wang, Yuelong Jiang, Alexander Tuzhilin
ICIP
2009
IEEE
14 years 8 months ago
An Efficient Bayesian Framework For On-line Action Recognition
On-line action recognition from a continuous stream of actions is still an open problem with fewer solutions proposed compared to time-segmented action recognition. The most chall...
ROBOCUP
2007
Springer
99views Robotics» more  ROBOCUP 2007»
14 years 1 months ago
Instance-Based Action Models for Fast Action Planning
Abstract. Two main challenges of robot action planning in real domains are uncertain action effects and dynamic environments. In this paper, an instance-based action model is lear...
Mazda Ahmadi, Peter Stone