Sciweavers

373 search results - page 27 / 75
» Building Relational World Models for Reinforcement Learning
Sort
View
ATC
2010
Springer
13 years 6 months ago
Agent-Augmented Co-Space: Toward Merging of Real World and Cyberspace
Co-Space refers to interactive virtual environment modelled after the real world we are situated in. Through realistic 3D modelling and animation technologies, Co-Space simulates t...
Ah-Hwee Tan, Yilin Kang
UAI
2008
13 years 9 months ago
Dyna-Style Planning with Linear Function Approximation and Prioritized Sweeping
We consider the problem of efficiently learning optimal control policies and value functions over large state spaces in an online setting in which estimates must be available afte...
Richard S. Sutton, Csaba Szepesvári, Alborz...
TBILLC
2005
Springer
14 years 1 months ago
Real World Multi-agent Systems: Information Sharing, Coordination and Planning
Abstract. Applying multi-agent systems in real world scenarios requires several essential research questions to be answered. Agents have to perceive their environment in order to t...
Frans C. A. Groen, Matthijs T. J. Spaan, Jelle R. ...
ALT
2010
Springer
13 years 9 months ago
Contrast Pattern Mining and Its Application for Building Robust Classifiers
: The ability to distinguish, differentiate and contrast between different data sets is a key objective in data mining. Such ability can assist domain experts to understand their d...
Kotagiri Ramamohanarao
ICCV
2011
IEEE
12 years 7 months ago
Relative Attributes
Human-nameable visual “attributes” can benefit various recognition tasks. However, existing techniques restrict these properties to categorical labels (for example, a person ...
Devi Parikh, Kristen Grauman