Pat Langley

"A Cognitive Architecture for Integrated Intelligent Agents"

Monday, March 12, 3:00 PM

Packard Lab - Room 416

In this talk I make two heretical claims. One is that the
field of artificial intelligence should devote far more attention to
developing integrated systems. The other is that cognitive psychology
has many useful ideas to offer about the design of such systems. I
review Newell's groundreaking notion of a cognitive architecture and I
describe Icarus, a specific architecture that unifies ideas from a
number of traditions. The framework supports the reactive execution of
routine skills, but it combines this ability with conceptual inference
to ensure informed behavior, and it associates skills with goals to
ensure relevant action. Icarus defaults to execution whenever an
applicable skill will achieve its current goal, but it falls back on
means-ends problem solving when it encounters an impasse. Moreover,
successful problem solving leads to the creation of new executable
skills that let the system achieve its goals more directly in the
future. Icarus' design incorporates insights from research on human
problem solving, reactive control, logical inference, and analytical
learning. The architecture differs from predecessors in its focus on
embodied agents, its commitment to hierarchical organizations of
knowledge, and its approach to the cumulative acquisition of these
structures. Icarus is consistent with many results from cognitive
pychology, but it also provides a realistic platform for developing
intelligent agents. I illustrate the framework's capabilities on tasks
from an in-city driving environment and an interactive computer game,
and I report experimental results on these and other domains.

This talk describes joint work with Nima Asgharbeygi, Dongkyu Choi,
Kirsten Cummings, Negin Nejati, Seth Rogers, Stephanie Sage, and
Daniel Shapiro at Stanford University.

Dr. Pat Langley serves as Director of the Institute for
the Study of Learning and Expertise, Professor of Computing and
Informatics at Arizona State University, and Head of the Computational
Learning Laboratory at Stanford's Center for the Study of Language and
Information. He has contributed to the fields of artificial
intelligence and cognitive science for over 25 years, having published
200 papers and five books on these topics, including the text Elements
of Machine Learning. Professor Langley is considered a co-founder of
the field of machine learning, where he championed both experimental
studies of learning algorithms and their application to real-world
problems before either were popular and before the phrase "data
mining" became widespread.

Dr. Langley is a Fellow of AAAI and the Cognitive Science Society, he
was founding Executive Editor of the journal Machine Learning, and he
was Program Chair for the Seventeenth International Conference on
Machine Learning. His research has dealt with learning in planning,
reasoning, language, vision, robotics, and scientific knowledge
discovery, and he has contributed novel methods to a variety of
paradigms, including logical, probabilistic, and case-based learning.
Dr. Langley's work on adaptive user interfaces introduced unobtrusive
ways to collect data about preferences and use them to offer
personalized services. His current research focuses on constructing
explanatory process models in scientific domains, and on learning and
transfer of hierarchical structures in cognitive architectures.