3274 search results - page 268 / 655 » Using Learning in a Control Agent |
112
click to vote
EMNLP
2009
15 years 9 days ago
2009
We examine the problem of overcoming noisy word-level alignments when learning tree-to-string translation rules. Our approach introduces new rules, and reestimates rule probabilit...
127
click to vote
IJCNN
2008
IEEE
15 years 9 months ago
2008
IEEE
— Current work is described wherein simplified versions of the Novamente Cognition Engine (NCE) are being used to control virtual agents in virtual worlds such as game engines an...
106
click to vote
AUSAI
2003
Springer
15 years 7 months ago
2003
Springer
Abstract. In the philosophy of behavior-based robotics, design of complex behavior needs the interaction of basic behaviors that are easily implemented. Action selection mechanism ...
100
click to vote
CAMP
2005
IEEE
15 years 8 months ago
2005
IEEE
—This paper describes a task-independent controller that allows for an easy implementation of vision systems for processing video sequences. The controller does not have a fixed ...
114
click to vote
ROBIO
2006
IEEE
15 years 8 months ago
2006
IEEE
— Humanoid robots are highly redundant systems with respect to the tasks they are asked to perform. This redundancy manifests itself in the number of degrees of freedom of the ro...