Intrinsically Motivated Reinforcement Learning

Abstract

Psychologists call behavior intrinsically motivated when it is engaged in for its own sake rather than as a step toward solving a specific problem of clear practical value. But what we learn during intrinsically motivated behavior is essential for our development as competent autonomous entities able to efficiently solve a wide range of practical problems as they arise. In this paper we present initial results from a computational study of intrinsically motivated reinforcement learning aimed at allowing artificial agents to construct and extend hierarchies of reusable skills that are needed for competent autonomy.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2005
Accession Number
ADA440280

Entities

People

  • Andrew G. Barto
  • Nuttapong Chentanez
  • Satinder Singh

Organizations

  • University of Massachusetts Amherst

Tags

Communities of Interest

  • Autonomy
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Applied Computer Science
  • Artificial Intelligence
  • Autonomous Agents
  • Computer Science
  • Computers
  • Dopamine
  • Environment
  • Information Operations
  • Learning
  • Machine Learning
  • Motivation
  • Probability
  • Psychological Phenomena And Processes
  • Reinforcement Learning
  • Side Effects

Fields of Study

  • Psychology

Readers

  • Systems Analysis and Design
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks