Learning in an Intentional System.

Abstract

The goal of the project, as outlined in the original proposal, was to carry out research aimed at the construction of adaptive planning systems that can learn in response to planning failures, i.e., modelling learning to plan as a process of debugging. Previous approaches to failure-driven learning, notably Sussman (1975), have been based on a traditional models of planning. in which the planner generates a monolithic, self-contained plan to be passed on to another module for execution. Such approaches have thus focused on the process of debugging a plan that has proven to be faulty during execution. However, such traditional models of planning have increasingly come under attack, as it has come to be recognized that planners operating in the real world must be reactive, changing plans on the fly to cope with unexpected circumstances. In such a model, there may be no single, monolithic plan that governs the systems behavior during execution.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1994
Accession Number
ADA291158

Entities

People

  • Greg Collins
  • Lawerence Birnbaum

Organizations

  • Northwestern University

Tags

Communities of Interest

  • Autonomy
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Air Force
  • Algorithms
  • Artificial Intelligence
  • Case Studies
  • Circuit Analysis
  • Cognitive Science
  • Computer Science
  • Computers
  • Control Systems
  • Detection
  • Engineering
  • Machine Learning
  • Models
  • New York
  • Specifications
  • Standards

Readers

  • Artificial Intelligence
  • Educational Psychology