Skill transfer through goal-driven representation mapping

In this paper, we present an approach to transfer that involves analogical mapping of symbols across different domains. We relate this mechanism to ICARUS, a theory of the human cognitive architecture. Our system can transfer skills across domains hypothesizing maps between representations, improving performance in novel domains. Unlike previous approaches to analogical transfer, our method uses an explanatory analysis that compares how well a new domain theory explains previous solutions under different mapping hypotheses. We present experimental evidence that the new mechanism improves transfer over ICARUS’ basic learning processes. Moreover, we argue that the same features which distinguish ICARUS from other architectures support representation mapping in a natural way and operate synergistically with it. These features enable our analogy system to translate a map among concepts into a map between skills, and to support transfer even if two domains are only partially analogous. We also discuss our system’s relation to other work on analogy and outline directions for future research. 2009 Elsevier B.V. All rights reserved.

[1]  P. Hayes,et al.  Analogy , 2000, Encyclopedic Dictionary of Archaeology.

[2]  Pat Langley,et al.  Structural Transfer of Cognitive Skills , 2007 .

[3]  Kenneth D. Forbus,et al.  Learning Domain Theories via Analogical Transfer , 2007 .

[4]  Pat Langley,et al.  Learning Recursive Control Programs from Problem Solving , 2006, J. Mach. Learn. Res..

[5]  Pat Langley,et al.  Learning hierarchical task networks by observation , 2006, ICML.

[6]  Pat Langley,et al.  A CONSTRAINED ARCHITECTURE FOR LEARNING AND PROBLEM SOLVING , 2005, Comput. Intell..

[7]  John E. Hummel,et al.  The One-to-One Constraint in Analogical Mapping and Inference , 2005, Cogn. Sci..

[8]  K. Holyoak,et al.  The Cambridge handbook of thinking and reasoning , 2005 .

[9]  Jaime G. Carbonell,et al.  Derivational Analogy in PRODIGY: Automating Case Acquisition, Storage, and Utilization , 1993, Machine Learning.

[10]  Dana S. Nau,et al.  SHOP2: An HTN Planning System , 2003, J. Artif. Intell. Res..

[11]  Brian Falkenhainer.  A Unified Approach to Explanation and Theory Formation , 2003 .

[12]  R. French.  The computational modeling of analogy-making , 2002, Trends in Cognitive Sciences.

[13]  Hector Muñoz-Avila,et al.  SHOP: Simple Hierarchical Ordered Planner , 1999, IJCAI.

[14]  C. Bishop.  The MIT Encyclopedia of the Cognitive Sciences , 1999 .

[15]  D. Gentner,et al.  Reasoning and learning by analogy. , 1997, The American psychologist.

[16]  Kurt VanLehn,et al.  Integration of Analogical Search Control and Explanation-Based Learning of Correctness , 1993 .

[17]  Richard Reviewer-Granger.  Unified Theories of Cognition , 1991, Journal of Cognitive Neuroscience.

[18]  Dedre Gentner,et al.  Systematicity as a Selection Constraint in Analogical Mapping , 1991, Cogn. Sci..

[19]  Raymond J. Mooney,et al.  A general explanation-based learning mechanism and its application to narrative understanding , 1990 .

[20]  Brian Falkenhainer,et al.  The Structure-Mapping Engine: Algorithm and Examples , 1989, Artif. Intell..

[21]  Paul Thagard,et al.  Analogical Mapping by Constraint Satisfaction , 1989, Cogn. Sci..

[22]  Rogers P. Hall,et al.  Computational Approaches to Analogical Reasoning: A Comparative Analysis , 1989, Artif. Intell..

[23]  John R. Anderson,et al.  A Keystroke Analysis of Learning and Transfer in Text Editing , 1987, SGCH.

[24]  Pat Langley,et al.  Learning, development, and production systems , 1987 .

[25]  A. Segre.  A learning apprentice system for mechanical assembly , 1987 .

[26]  David E. Kieras,et al.  The Acquisition of Procedures from Text: A Production-System Analysis of Transfer of Training. Technical Report No. 16. , 1985 .

[27]  Dedre Gentner,et al.  Structure-Mapping: A Theoretical Framework for Analogy , 1983, Cogn. Sci..

[28]  Patrick Henry Winston,et al.  Learning New Principles from Precedents and Exercises , 1982, Artif. Intell..

[29]  M. Lio,et al.  Cognitive Systems Research , 2023 .