Embedded Incremental Feature Selection for Reinforcement Learning

Abstract

Classical reinforcement learning techniques become impractical in domains with large complex state spaces. The size of a domain's state space is dominated by the number of features used to describe the state. Fortunately, in many real-world environments learning an effective policy does not usually require all the provided features. In this paper we present a feature selection algorithm for reinforcement learning called Incremental Feature Selection Embedded in NEAT (IFSE-NEAT) that incorporates sequential forward search into neuroevolutionary algorithm NEAT. We provide an empirical analysis on a realistic simulated domain with many irrelevant and relevant features. Our results demonstrate that IFSE-NEAT selects smaller and more effective feature sets than alternative approaches, NEAT and FS-NEAT, and superior performance characteristics as the number of available features increases.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 2012
Accession Number
ADA563362

Entities

People

  • Lei Yu
  • Robert Wright
  • Steven Loscalzo

Organizations

  • Air Force Research Laboratory

Tags

Communities of Interest

  • Autonomy
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Air Force Research Laboratories
  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Computer Programming
  • Computer Science
  • Computers
  • Dimensionality Reduction
  • Environment
  • Feature Selection
  • Learning
  • Machine Learning
  • Network Topology
  • Neural Networks
  • Range Finders
  • Reinforcement Learning
  • Topology

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.

Technology Areas

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