Automatic State Space Aggregation Using a Density Based Technique

Abstract

applying reinforcement learning techniques in continuous environments is challenging because there are infinitely many states to visit in order to learn an optimal policy. To make this situation tractable, abstractions are often used to reduce the infinite state space down to a small and finite one. Some of the more powerful and commonplace abstractions, tiling abstractions such as CMAC, work by aggregating many base states into a single abstract state. Unfortunately, significant manual effort is often necessary in order to apply them to non-trivial control problems. Here we develop an automatic state space aggregation algorithm, Maximum Density Separation, which can produce a meaningful abstraction with minimal manual effort. This method leverages the density of observations in the space to construct a partition and aggregate states in a dense region to the same abstract state. We show that the abstractions produced by this method on two benchmark reinforcement learning problems can outperform fixed tiling methods in terms of both the convergence rate of a learning algorithm and the number of abstract states needed.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 2012
Accession Number
ADA563366

Entities

People

  • Robert Wright
  • Steven Loscalzo

Organizations

  • Air Force Research Laboratory

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Abstracts
  • Air Force Research Laboratories
  • Algorithms
  • Artificial Intelligence
  • Automatic
  • Computer Science
  • Convergence
  • Dimensionality Reduction
  • Environment
  • Ground State
  • Information Processing
  • Information Systems
  • Learning
  • Machine Learning
  • Neural Networks
  • Observation
  • Reinforcement Learning

Fields of Study

  • Computer science
  • Engineering
  • Geography

Readers

  • Applied Combinatorial Optimization and Logic Circuit Design.
  • Distributed Systems and Data Platform Development
  • Neural Network Machine Learning.

Technology Areas

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