Sciweavers

754 search results - page 64 / 151
» Learning executable agent behaviors from observation
Sort
View
KDD
2007
ACM
192views Data Mining» more  KDD 2007»
16 years 4 months ago
Active exploration for learning rankings from clickthrough data
We address the task of learning rankings of documents from search engine logs of user behavior. Previous work on this problem has relied on passively collected clickthrough data. ...
Filip Radlinski, Thorsten Joachims
AGI
2011
14 years 8 months ago
Learning Problem Solving Skills from Demonstration: An Architectural Approach
We present an architectural approach to learning problem solving skills from demonstration, using internal models to represent problem-solving operational knowledge. Internal forwa...
Haris Dindo, Antonio Chella, Giuseppe La Tona, Mon...
144
Voted
CSL
1998
Springer
15 years 4 months ago
Evaluating spoken dialogue agents with PARADISE: Two case studies
This paper presents PARADISE PARAdigm for DIalogue System Evaluation, a general framework for evaluating and comparing the performance of spoken dialogue agents. The framework d...
Marilyn A. Walker, Diane J. Litman, Candace A. Kam...
DAGSTUHL
2003
15 years 5 months ago
Removing Some 'A' from AI: Embodied Cultured Networks
We embodied networks of cultured biological neurons in simulation and in robotics. This is a new research paradigm to study learning, memory, and information processing in real tim...
Douglas J. Bakkum, Alexander C. Shkolnik, Guy Ben-...
ICPP
2006
IEEE
15 years 10 months ago
Performance Modeling based on Multidimensional Surface Learning for Performance Predictions of Parallel Applications in Non-Dedi
Modeling the performance behavior of parallel applications to predict the execution times of the applications for larger problem sizes and number of processors has been an active ...
Jay Yagnik, H. A. Sanjay, Sathish S. Vadhiyar