Varieties of learning in Soar: 1987

Abstract : Soar is an architecture for intelligence that integrates learning into all of its problem-solving behavior. The learning mechanism, chunking, has been studied experimentally in a broad range of tasks and situations. This paper summarizes the research on chucking in Soar, covering the effects of chunking in different tasks, task-independent applications of chunking and our theoretical analyses of effects and limits of chunking. We discuss what and when Soar has been able to learn so far. The results demonstrate that the variety of learning in Soar arises from variety in problem solving, rather than from variety in architectural mechanisms. Keywords: Artificial intelligence, Machine learning, cognitive architecture.

[1]  John E. Laird,et al.  Learning General Search Control from Outside Guidance , 1987, IJCAI.

[2]  David M. Steier CYPRESS-Soar: A Case Study in Search and Learning in Algorithm Design , 1987, IJCAI.

[3]  R. Seibel DISCRIMINATION REACTION TIME FOR 1,023-ALTERNATIVE TASK. , 1963, Journal of experimental psychology.

[4]  Earl D. Sacerdoti,et al.  Planning in a Hierarchy of Abstraction Spaces , 1974, IJCAI.

[5]  Tom Michael Mitchell,et al.  Explanation-based generalization: A unifying view , 1986 .

[6]  Allen Newell,et al.  Knowledge Level Learning in Soar , 1987, AAAI.

[7]  Tom M. Mitchell,et al.  LEAP: A Learning Apprentice for VLSI Design , 1985, IJCAI.

[8]  Amy Unruh,et al.  Dynamic abstraction problem solving in Soar , 1993 .

[9]  Sridhar Mahadevan,et al.  Verification-based Learning: A Generalized Strategy for Inferring Problem-Reduction Methods , 1985, IJCAI.

[10]  Allen Newell,et al.  R1-Soar: An Experiment in Knowledge-Intensive Programming in a Problem-Solving Architecture , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  John E. Laird,et al.  Overgeneralization during knowledge compilation in Soar , 1993 .

[12]  Richard Fikes,et al.  Learning and Executing Generalized Robot Plans , 1993, Artif. Intell..

[13]  R. Siegler Children's Thinking : What Develops? , 1978 .

[14]  Clare Bates Congdon,et al.  The Soar User''''s Manual , 1986 .

[15]  Allen Newell,et al.  SOAR: An Architecture for General Intelligence , 1987, Artif. Intell..

[16]  John E. Laird,et al.  Meta-levels in Soar , 1993 .

[17]  Douglas R. Smith,et al.  Top-Down Synthesis of Divide-and-Conquer Algorithms , 1985, Artif. Intell..

[18]  P. Johnson-Laird,et al.  Mental Models: Towards a Cognitive Science of Language, Inference, and Consciousness , 1985 .

[19]  Allen Newell,et al.  Towards Chunking as a General Learning Mechanism , 1984, AAAI.

[20]  H. Simon,et al.  EPAM-like Models of Recognition and Learning , 1984, Cogn. Sci..

[21]  Patrick Henry Winston,et al.  The psychology of computer vision , 1976, Pattern Recognit..

[22]  Guy L. Steele,et al.  The definition and implementation of a computer programming language based on constraints , 1980 .

[23]  R. Korf Learning to solve problems by searching for macro-operators , 1983 .

[24]  John E. Laird,et al.  Mapping Explanation-Based Generalization onto Soar , 1986, AAAI.

[25]  Allen Newell,et al.  The chunking of goal hierarchies: a generalized model of practice , 1993 .