Constructing Abstraction Hierarchies for Robust, Real-Time Control

Abstract

This project primarily focused on the theoretical principles underlying which high-level actions an agent should build, and data-efficient algorithms for learning those high-level actions from interaction with an agent's environment. The projected funded a single PhD student for three years, and resulted in 5 publications at top-tier, highly-refereed international conferences, and 3 additional publications either in preparation or currently under review. The report describes these research results and draws appropriate conclusions.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 22, 2020
Accession Number
AD1103140

Entities

People

  • George Konidaris

Organizations

  • Brown University

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Abstracts
  • Air Force
  • Air Force Research Laboratories
  • Algorithms
  • Artificial Intelligence
  • Coverings
  • Deep Learning
  • Environment
  • Hierarchies
  • Information Processing
  • Information Systems
  • Iterations
  • Learning
  • Machine Learning
  • Markov Processes
  • Mathematical Analysis
  • Probability
  • Random Walk
  • Reinforcement Learning
  • Scientific Research
  • Universities

Readers

  • Distributed Systems and Data Platform Development
  • Systems Analysis and Design
  • Technical Research and Report Writing.