The Soar Papers: Research on Integrated Intelligence
Volume One: 1969-1988
edited by Paul S. Rosenbloom, John E. Laird, and Alan Newell
(c) 1993 Massachusetts Institute of Technology
ISBN 0-262-68071-8 (pbk)
Soar is a state-of-the-art computational theory of the mind hat has had a significant impact in both artificial intelligence and cognitive science. Begun by John E. Laird, Allen Newell, and Paul S. Rosenbloom at Carnegie Mellon in the early 1980s, the Soar Project is an investigation into the architecture underlying intelligent behaviour with the goal of developing and applying a unified theory of natural and artificial intelligence. The Soar Papers - sixty-three articles in all - provides in one place the important ideas that have emerged from this project.
The book is organized chronologically, with an introduction that provides multiple according to major topics. Readers interested in the entire effort can read the articles in publication order, while readers interested only in a specific topic can go directly to a logical sequence of papers to read on that topic.
Paul S. Rosenbloom is Associate Professor of Computer Science at the Information Sciences Institute. John E. Laird is Associate Professor of Electrical Engineering and Computer Science at the University of Michigan. The late Allen Newell was U.A. and Helen Whitaker University Professor of Computer Science at Carnegie Mellon University.
The Soar Papers is included in the MIT Press Artificial Intelligence Series, edited by Michael Brady, Daniel Bobrow, and Randall Davis.
Some of the authors
===================
Alan Newell - (1927-1992) Department of Computer Science, Carnegie-Mellon University, Pittsburgh
Paul S. Rosenbloom - Department of Computer Science, Carnegie-Mellon University, Pittsburgh
Knowledge Systems Laboratory, Department of Computer Science, Stanford University
Information Sciences Institute, University of Southern California
John E. Laird - Department of Electrical Engineering and Computer Science, University of Michigan,
John P. McDermott - Author of "R1: an Expert in the Computer Systems Domain" (1980)
Thad A. Polk - University of Michigan, Department of Psychology
Olin G. Shivers - Northeastern University, Boston, Mass.
Amy Unruh - University of Melbourne
Daniel J. Scales - Department of Computer Science, Stanford University
Andrew R. Golding - Mitsubishi Electric Research Laboratory, 201 Broadway, Cambridge
David M. Steier - Carnegie Mellon Univ. Pittsburgh
Author(s): Paul S. Rosenbloom, John E. Laird, and Alan Newell (editors)
Edition: 1
Publisher: MIT Press
Year: 1993
Language: English
Pages: 770
City: Cambridge, Massachusetts
Acknowledgments / XIII
Introduction / XIX
1969-1982
---------
3 - Heuristic Programming: Ill-Structured Problems
A. Newell
55 - Reasoning, Problem Solving, and Decision Processes: The Problem Space as a Fundamental Category
A. Newell
81 - Mechanisms of Skill Acquisition and the Law of Practice
A. Newell and P.S. Rosenbloom
136 - The Knowledge Level
A. Newell
177 - Learning by Chunking: A Production-System Model of Practice
P.S. Rosenbloom and A. Newell
1983-1985
---------
245 - A Universal Weak Method
J.E. Laird and A. Newell
293 - The Chunking of Goal Hierarchies: A Generalized Model of Practice
P.S. Rosenbloom and A. Newell
335 - Towards Chunking as a General Learning Mechanism
J.E. Laird, P.S. Rosenbloom, and A. Newell
340 - R1-Soar: An Experiment in Knowledge-Intensive Programming in a Problem-Solving Architecture
P.S. Rosenbloom, J.E. Laird, J. McDermott, A. Newell, and E. Orciuch
1986
----
351 - Chunking in Soar: The Anatomy of a General Learning Mechanism
J.E. Laird, P.S. Rosenbloom, and A. Newell
387 - Overgeneralization During Knowledge Compilation in Soar
J.E. Laird, P.S. Rosenbloom, and A. Newell
399 - Mapping Explanation-based Generalization onto Soar
P.S. Rosenbloom and J.E. Laird
406 - Efficient Matching Algorithms for the Soar/OPS5 Production System
D.J. Scales
1987
----
459 - Learning General Search Control from Outside Guidance
A.R. Golding, P.S. Rosenbloom, and J.E. Laird
463 - Soar: An Architecture for General Intelligence
J.E. Laird, A. Newell, and P.S. Rosenbloom
527 - Knowledge Level Learning in Soar
P.S. Rosenbloom, J.E. Laird, and A. Newell
533 - CYPRESS-Soar: A Case Study in Search and Learning in Algorithm Design
D.M. Steier
537 - Varities of Learning in Soar: 1987
D.M. Steier, J.E. Laird, A. Newell, P.S. Rosenbloom, R. Flynn, A. Golding. T.A. Polk, O.G. Shivers, A. Unruh, G.R. Yost
549 - Dynamic Abstraction Problem Solving in Soar,
A. Unruh, P.S. Rosenbloom, and J.E. Laird
1988
----
563 - Electronic Mail and Scientific Communication: A Study of the Soar Extended Research Group
K. Carley and K. Wendt
598 - Placing Soar on the Connection Machine
R. Flynn
615 - Recovery from Incorrect Knowledge in Soar
J.E. Laird
621 - Comparison of the Rete and Treat Production Matchers for Soar (A Summary)
P.Nayak, A. Gupta, and P.S. Rosenbloom
627 - Modeling Human Syllogistic Reasoning in Soar
T.A. Polk and A. Newell
634 - Beyond Generalization as Search: Towards a Unified Framework for the Acquisition of New Knowledge
P.S. Rosenbloom
639 - Meta-Levels in Soar
P.S. Rosenbloom, J.E. Laird and A. Newell
653 - Integrating Multiple Sources of Knowledge into Designer-Soar: An Automatic Algorithm Designer
D.M. Steier, A. Newell
659 - Soar/PSM-E: Investigating Match Parallelism in a Learning Production System
M. Tambe, D. Kalp, A. Gupta, C.L. Forgy, B.G. Milnes, and A.Newell
674 - Applying Problem Solving and Learning to Diagnosis
R.Washington and P.S. Rosenbloom
688 - Learning new Tasks in Soar
G.R. Yost and A. Newell
703 - Index A-1
