Sciweavers

8949 search results - page 1501 / 1790
» is 1998
Sort
View
AAAI
1998
15 years 8 months ago
Applying Online Search Techniques to Continuous-State Reinforcement Learning
In this paper, we describe methods for e ciently computing better solutions to control problems in continuous state spaces. We provide algorithms that exploit online search to boo...
Scott Davies, Andrew Y. Ng, Andrew W. Moore
AAAI
1998
15 years 8 months ago
Bayesian Q-Learning
A central problem in learning in complex environmentsis balancing exploration of untested actions against exploitation of actions that are known to be good. The benefit of explora...
Richard Dearden, Nir Friedman, Stuart J. Russell
AAAI
2000
15 years 8 months ago
Using Prior Knowledge: Problems and Solutions
Encoding knowledge is time consuming and expensive. A possible solution to reduce the cost of developing a new knowledge base (KB) is to reuse existing knowledge. Previous work ad...
Vinay K. Chaudhri, Mark E. Stickel, Jér&oci...
AAAI
1998
15 years 8 months ago
Toward Design as Collaboration
In design, multiple disparate goals must be addressed simultaneously. It is the thesis of this work that problems in two-dimensional layout design can be solved by collaboration a...
Susan L. Epstein
AAAI
1998
15 years 8 months ago
TRIPS: An Integrated Intelligent Problem-Solving Assistant
We discuss what constitutes an integrated system in AI, and why AI researchers should be interested in building and studying them. Taking integrated systems to be ones that integr...
George Ferguson, James F. Allen
« Prev « First page 1501 / 1790 Last » Next »