Accession Number : ADA311505

Title :   Memory-Based Learning for Control.

Descriptive Note : Technical rept.,

Corporate Author : CARNEGIE-MELLON UNIV PITTSBURGH PA ROBOTICS INST

Personal Author(s) : Moore, A. W. ; Atkeson, C. G. ; Schaal, S. A.

PDF Url : ADA311505

Report Date : APR 1995

Pagination or Media Count : 42

Abstract : The central thesis of this article is that memory-based methods provide natural powerful mechanisms for high-anatomy learning control. This paper takes the form of a survey of the ways in which memory-based methods can and have been applied to control tasks, with an emphasis on tasks in robotics and manufacturing. We explain the various forms that control tasks can take, and how this impacts on the choice of learning algorithm. We show a progression of five increasingly more complex algorithms which are applicable to increasingly more complex kinds of control tasks. We examine their empirical behavior on robotic and industrial tasks. The final section discusses the interesting impact that explicitly remembering all previous experiences has on the problem of learning control.

Descriptors :   *LEARNING MACHINES, *CONTROL THEORY, MATHEMATICAL MODELS, ALGORITHMS, IMAGE PROCESSING, ROBOTICS, NEURAL NETS, OPTIMIZATION, DATA MANAGEMENT, REAL TIME, INPUT OUTPUT PROCESSING, RULE BASED SYSTEMS, REGRESSION ANALYSIS, NONLINEAR SYSTEMS, SYSTEMS ANALYSIS, COMPUTER AIDED MANUFACTURING, COMPUTER AIDED INSTRUCTION, DYNAMIC PROGRAMMING, AUTOMATIC PROGRAMMING.

Subject Categories : Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE