Learning Models of Unknown Events

Abstract

Agents with incomplete models of their environment are likely to be surprised by it. For agents in immense environments that defy complete modeling, this represents an opportunity to learn. We investigate approaches for situated agents to detect surprise, discriminate among different forms of surprise, and ultimately hypothesize new models for the unknown events that surprised them. We instantiate these approaches in a new goal reasoning agent, FooLMETWICE, and investigate how that agent performs in a simulated environment. In this case study, we found that FooLMETWicE learn models that substantially improve its performance.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 14, 2013
Accession Number
ADA603399

Entities

People

  • David W. Aha
  • Matthew Molineaux

Organizations

  • United States Naval Research Laboratory

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Autonomous Underwater Vehicles
  • Biological Phenomena
  • Case Studies
  • Ecological And Environmental Phenomena
  • Engineering
  • Environment
  • Information Operations
  • Learning
  • Mental Processes
  • Military Research
  • Psychological Phenomena And Processes
  • Reasoning
  • Underwater Vehicles
  • Vehicles

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Irregular Warfare and Special Operations Cyberspace Operations against Adversarial Threats.
  • Systems Analysis and Design