Sciweavers

1233 search results - page 168 / 247
» Reinforcement Learning in MirrorBot
Sort
View
RAS
2010
109views more  RAS 2010»
14 years 8 months ago
Combining active learning and reactive control for robot grasping
Grasping an object is a task that inherently needs to be treated in a hybrid fashion. The system must decide both where and how to grasp the object. While selecting where to grasp...
Oliver Krömer, Renaud Detry, Justus H. Piater...
ICMLA
2010
14 years 7 months ago
Robust Learning for Adaptive Programs by Leveraging Program Structure
Abstract--We study how to effectively integrate reinforcement learning (RL) and programming languages via adaptation-based programming, where programs can include non-deterministic...
Jervis Pinto, Alan Fern, Tim Bauer, Martin Erwig
UM
2010
Springer
14 years 7 months ago
Inducing Effective Pedagogical Strategies Using Learning Context Features
Effective pedagogical strategies are important for e-learning environments. While it is assumed that an effective learning environment should craft and adapt its actions to the use...
Min Chi, Kurt VanLehn, Diane J. Litman, Pamela W. ...
CEC
2010
IEEE
14 years 10 months ago
Coevolutionary Temporal Difference Learning for small-board Go
—In this paper we apply Coevolutionary Temporal Difference Learning (CTDL), a hybrid of coevolutionary search and reinforcement learning proposed in our former study, to evolve s...
Krzysztof Krawiec, Marcin Szubert
ECCV
2010
Springer
15 years 1 months ago
Discriminative Tracking by Metric Learning
We present a discriminative model that casts appearance modeling and visual matching into a single objective for visual tracking. Most previous discriminative models for visual tra...