9/17/1998
3:45pm-4:45pm
ECCR 265
|
How the Agent Got Its Design: Case Studies in Agent Evaluation
Colorado State University
Many AI researchers view evaluation as a burden; it takes too long, gets in the
way of rapid prototyping and is not well supported by methods and tools. This
talk will present two projects focused on developing agents and show how the
evaluation process influenced their designs.
The first project is SavvySearch, a WWW meta-search engine, which was designed
based on a series of experiments in which we actively and passively solicited
user feedback. In the second project, we are implementing a multi-layer control
system for two simulated robot environments; evaluation has helped us alleviate
the practical problem of getting other people's algorithms to work in our
application.
In conjunction with the University of Massachusetts, the lessons, methods and
tools discovered through these projects and others are being made available at
a web repository.
Refreshments will be served immediately before the talk at 3:30pm.
|
The Department holds colloquia throughout the Fall and Spring semesters. These
colloquia, open to the public, are typically held on Thursday afternoons, but
sometimes occur at other times as well.
If you would like to receive email notification of upcoming colloquia,
subscribe to our
Colloquia Mailing List.
If you would like to schedule a colloquium, see
Colloquium Scheduling.
Sign language interpreters are available upon request. Please contact
Stephanie Morris at least five days prior to the colloquium.
|
