A Series of Unlikely Events: Learning from Sequential Behavior for Activity Based Intelligence and Modeling Human Expertise

Abstract

Main Takeaway: Inverse Reinforcement Learning (IRL) takes a set of observed behaviors (captured in data) by one or more agents, and learns the preferences agents have that describe to observed behaviors.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2020
Accession Number
AD1110305

Entities

People

  • Eric Heim

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Ground and Sea Platforms

DTIC Thesaurus Topics

  • Automatic
  • Automatic Identification Systems
  • Coast Guard
  • Data Sets
  • Demonstrations
  • Department Of Defense
  • Detectors
  • Engineering
  • Feature Selection
  • Guarantees
  • Identification
  • Identification Systems
  • Learning
  • Materials
  • Reinforcement Learning
  • Software Development
  • Universities

Fields of Study

  • Economics

Readers

  • Brain and Cognitive Science; Experimental Psychology; Cognitive Neuroscience
  • Educational Psychology
  • Military Training and Readiness Simulation

Technology Areas

  • AI & ML