Understanding the Adverse Effects of Accelerating Reinforcement Learning with Human Trainers

Abstract

Recent advances in reinforcement learning (RL) have propelled the idea that artificially intelligent agents may one day replace humans in performing complex tasks. There are numerous challenges associated with moving RL from a simulated environment to the real world. In particular, understanding the decision making process of the RL agents and ascertaining the viability of use in safety-constrained environments are key challenges. An evolving approach to addressing these challenges is to impart human knowledge into the learning algorithms. Through a comprehensive evaluation using a Pong RL agent, this thesis provides evidence that incorporating human influence into an RL algorithm can cause a strategy conflict and impede learning. In particular, it shows that (i) there is an inflection point measured by training episodes with respect to the positive effect of incorporating human influence for the Pong agent, and that (ii) if human influence is not decayed beyond the inflection point, the negative effect can intensify and eventually undo all prior training gains.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2020
Accession Number
AD1126458

Entities

People

  • Brandon R Hee

Organizations

  • Naval Postgraduate School

Tags

Communities of Interest

  • Autonomy
  • Energy and Power Technologies
  • Human Systems

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Automata Theory
  • California
  • Computer Languages
  • Computer Programming
  • Computer Programs
  • Computer Science
  • Computers
  • Convolutional Neural Networks
  • Graphics Processing Unit
  • High Performance Computing
  • Information Processing
  • Information Science
  • Information Systems
  • Instructors
  • Machine Learning
  • Network Science
  • Neural Networks
  • Operating Systems
  • Probability

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Systems Analysis and Design

Technology Areas

  • AI & ML