Curriculum Development for Transfer Learning in Dynamic Multiagent Settings

Abstract

Transfer learning in reinforcement learning has been an active area of research over the past decade. In transfer learning, training on a source task is leveraged to speed up or otherwise improve learning on a target task. This project addressed the ambitious problem of curriculum learning in reinforcement learning, in which the goal is to design a sequence of source tasks for an agent to train on, such that final performance or learning speed is improved. We take the position that each stage of such a curriculum should be tailored to the ability of the agent in order to promote learning new behaviors. To tackle the problem of curriculum learning, we addressed three key sub-problems: 1) Learning Transferability, and 2) Automatic Source Task Creation, 3) Curriculum Construction through Crowd Sourcing. This technical report documents the methods, experiments, and results of the proposed frameworks for curriculum construction for reinforcement learning agents.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2016
Accession Number
AD1011857

Entities

People

  • Jivko Sinapov
  • Matthew Taylor
  • Peter Stone

Organizations

  • University of Texas at Austin

Tags

Communities of Interest

  • Autonomy
  • Counter WMD
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Air Force
  • Air Force Research Laboratories
  • Algorithms
  • Animal Training
  • Automatic
  • Computational Science
  • Construction
  • Curriculum
  • Education
  • Government Procurement
  • Language
  • Machine Learning
  • Probability
  • Reinforcement Learning
  • Sequences
  • Supervised Machine Learning
  • Training

Fields of Study

  • Computer science
  • Education

Readers

  • Artificial Intelligence
  • Instructional Design and Training Evaluation.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks