Memory-Based Learning for Control.

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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 01, 1995
Accession Number
ADA311505

Entities

People

  • A. W. Moore
  • C. G. Atkeson
  • S. A. Schaal

Organizations

  • Carnegie Mellon University

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Learning
  • Manufacturing
  • Mathematics
  • Robotics

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - Neural Networks
  • Autonomy
  • Autonomy - Autonomous System Control