Hierarchical Reinforcement in Continuous State and Multi-Agent Environments

Abstract

This dissertation investigates the use of hierarchy and abstraction as a means of solving complex sequential decision making problems such as those with continuous state and/or continuous action spaces, and domains with multiple cooperative agents. This thesis develops several novel extensions to hierarchical reinforcement learning (HRL), and designs algorithms that are appropriate for such problems. It has been shown that the average reward optimality criterion is more natural than the more commonly used discounted criterion for continuing tasks. This thesis investigates two formulations of HRL based on the average reward semi-Markov decision process (SMDP) model, both for discrete-time and continuous-time. These formulations correspond to two notions of optimality that have been explored in previous work on HRL: hierarchical optimality and recursive optimality. Novel discrete-time and continuous-time algorithms, termed hierarchically optimal average reward RL (HAR) and recursively optimal average reward RL (RAR) are presented, which learn to find hierarchically and recursively optimal average reward policies. Two automated guided vehicle (AGV) scheduling problems are used as experimental testbeds to empirically study the performance of the proposed algorithms.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2005
Accession Number
ADA438689

Entities

People

  • Mohammad Ghavamzadeh

Organizations

  • University of Massachusetts Amherst

Tags

Communities of Interest

  • Autonomy
  • C4I
  • Human Systems

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Automated Guided Vehicles
  • Computational Science
  • Computer Programming
  • Computer Science
  • Computers
  • Information Processing
  • Information Systems
  • Machine Learning
  • Multiagent Systems
  • Neural Networks
  • Operations Research
  • Probability
  • Probability Distributions
  • Random Variables
  • Sensor Networks
  • Systems Engineering

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Mathematical Modeling and Probability Theory.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • Space
  • Space - Spacecraft Maneuvers