Guiding Autonomous Agents to Better Behaviors through Human Advice

Abstract

Inverse Reinforcement Learning (IRL) is an approach for domain-reward discovery from demonstration, where anagent mines the reward function of a Markov decision process by observing an expert acting in the domain. In thestandard setting, it is assumed that the expert acts (nearly) optimally, and a large number of trajectories, i.e.,training examples are available for reward discovery (and consequently, learning domain behavior). These are notpractical assumptions: trajectories are often noisy, and there can be a paucity of examples.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 07, 2013
Accession Number
AD1014223

Entities

People

  • Gautam Kunapuli
  • Jude W. Shavlik
  • Phillip Odom
  • Sriraam Natarajan

Organizations

  • Indiana University

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Air Force Research Laboratories
  • Algorithms
  • Artificial Intelligence
  • Autonomous Agents
  • Bayesian Networks
  • Cognitive Science
  • Computational Science
  • Computer Science
  • Data Mining
  • Information Science
  • Machine Learning
  • Military Research
  • Network Science
  • Probability
  • Reinforcement Learning
  • Simulators
  • Supervised Machine Learning

Fields of Study

  • Computer science

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms