Sciweavers

350 search results - page 55 / 70
» Complexity of Planning with Partial Observability
Sort
View
NN
2010
Springer
125views Neural Networks» more  NN 2010»
13 years 6 months ago
Parameter-exploring policy gradients
We present a model-free reinforcement learning method for partially observable Markov decision problems. Our method estimates a likelihood gradient by sampling directly in paramet...
Frank Sehnke, Christian Osendorfer, Thomas Rü...
IJCV
2010
574views more  IJCV 2010»
13 years 6 months ago
Time-Delayed Correlation Analysis for Multi-Camera Activity Understanding
We propose a novel approach to understanding activities from their partial observations monitored through multiple non-overlapping cameras separated by unknown time gaps. In our...
Chen Change Loy, Tao Xiang, Shaogang Gong
ICRA
2007
IEEE
150views Robotics» more  ICRA 2007»
14 years 2 months ago
A Motion Planner for a Hybrid Robotic System with Kinodynamic Constraints
— The rapidly increasing complexity of tasks robotic systems are expected to carry out underscores the need for the development of motion planners that can take into account disc...
Erion Plaku, Lydia E. Kavraki, Moshe Y. Vardi
KI
2004
Springer
14 years 1 months ago
Shape-Based Robot Mapping
We present a novel geometric model for robot mapping suited for robots equipped with a laser range finder. The geometric representation is based on shape. Cyclic ordered sets of p...
Diedrich Wolter, Longin Jan Latecki, Rolf Lakä...
ENTCS
2006
109views more  ENTCS 2006»
13 years 7 months ago
Incremental Verification for On-the-Fly Controller Synthesis
The CIRCA system automatically synthesizes hard real-time discrete event controllers from plant and environment descriptions. CIRCA's automatically-synthesized controllers pr...
David J. Musliner, Michael J. S. Pelican, Robert P...