"A Value-Driven Architecture for Intelligent Behavior"
                             Pat Langley
               Computational Learning Laboratory, CSLI
                  http://cll.stanford.edu/~langley/

In this talk, I describe Icarus, an integrated cognitive architecture
for intelligent agents in which affective values play a central role.
The framework incorporates long-term and short-term memories for
concepts and skills, and it includes mechanisms for recognizing
concepts, calculating reward, nominating and selecting skills based on
expected values, executing those skills in a reactive manner,
repairing these skills when they fail, and abandoning them when they
promise poor returns.  I illustrate these processes with examples from
the domain of highway driving.  Icarus differs from earlier cognitive
architectures like ACT and Soar by giving categorization and execution
primacy over problem solving and by giving affective values a central
role in determining agent behavior.

This talk describes joint work with Daniel Shapiro, Meg Aycinena, and
Michael Siliski.